29 files changed, 1865 insertions, 168 deletions

diff --git a/README.md b/README.md
index 8a4ffade..55990581 100644
--- a/README.md
+++ b/README.md
@@ -135,6 +135,7 @@ The documentation was moved from this README over to the project's [wiki](https:
 - SwinIR - https://github.com/JingyunLiang/SwinIR

 - Swin2SR - https://github.com/mv-lab/swin2sr

 - LDSR - https://github.com/Hafiidz/latent-diffusion

+- MiDaS - https://github.com/isl-org/MiDaS

 - Ideas for optimizations - https://github.com/basujindal/stable-diffusion

 - Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.

 - Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)

diff --git a/extensions-builtin/LDSR/ldsr_model_arch.py b/extensions-builtin/LDSR/ldsr_model_arch.py
index 90e0a2f0..a87d1ef9 100644
--- a/extensions-builtin/LDSR/ldsr_model_arch.py
+++ b/extensions-builtin/LDSR/ldsr_model_arch.py
@@ -22,6 +22,7 @@ class LDSR:
         pl_sd = torch.load(self.modelPath, map_location="cpu")
         sd = pl_sd["state_dict"]
         config = OmegaConf.load(self.yamlPath)
+        config.model.target = "ldm.models.diffusion.ddpm.LatentDiffusionV1"
         model = instantiate_from_config(config.model)
         model.load_state_dict(sd, strict=False)
         model.cuda()
diff --git a/extensions-builtin/LDSR/scripts/ldsr_model.py b/extensions-builtin/LDSR/scripts/ldsr_model.py
index 1cef29a4..5c96037d 100644
--- a/extensions-builtin/LDSR/scripts/ldsr_model.py
+++ b/extensions-builtin/LDSR/scripts/ldsr_model.py
@@ -7,7 +7,7 @@ from basicsr.utils.download_util import load_file_from_url
 from modules.upscaler import Upscaler, UpscalerData
 from ldsr_model_arch import LDSR
 from modules import shared, script_callbacks
-import sd_hijack_autoencoder
+import sd_hijack_autoencoder, sd_hijack_ddpm_v1
 
 
 class UpscalerLDSR(Upscaler):
diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py
new file mode 100644
index 00000000..5c0488e5
--- /dev/null
+++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py
@@ -0,0 +1,1449 @@
+# This script is copied from the compvis/stable-diffusion repo (aka the SD V1 repo)
+# Original filename: ldm/models/diffusion/ddpm.py
+# The purpose to reinstate the old DDPM logic which works with VQ, whereas the V2 one doesn't
+# Some models such as LDSR require VQ to work correctly
+# The classes are suffixed with "V1" and added back to the "ldm.models.diffusion.ddpm" module
+
+import torch
+import torch.nn as nn
+import numpy as np
+import pytorch_lightning as pl
+from torch.optim.lr_scheduler import LambdaLR
+from einops import rearrange, repeat
+from contextlib import contextmanager
+from functools import partial
+from tqdm import tqdm
+from torchvision.utils import make_grid
+from pytorch_lightning.utilities.distributed import rank_zero_only
+
+from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
+from ldm.modules.ema import LitEma
+from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
+from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
+from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
+from ldm.models.diffusion.ddim import DDIMSampler
+
+import ldm.models.diffusion.ddpm
+
+__conditioning_keys__ = {'concat': 'c_concat',
+                         'crossattn': 'c_crossattn',
+                         'adm': 'y'}
+
+
+def disabled_train(self, mode=True):
+    """Overwrite model.train with this function to make sure train/eval mode
+    does not change anymore."""
+    return self
+
+
+def uniform_on_device(r1, r2, shape, device):
+    return (r1 - r2) * torch.rand(*shape, device=device) + r2
+
+
+class DDPMV1(pl.LightningModule):
+    # classic DDPM with Gaussian diffusion, in image space
+    def __init__(self,
+                 unet_config,
+                 timesteps=1000,
+                 beta_schedule="linear",
+                 loss_type="l2",
+                 ckpt_path=None,
+                 ignore_keys=[],
+                 load_only_unet=False,
+                 monitor="val/loss",
+                 use_ema=True,
+                 first_stage_key="image",
+                 image_size=256,
+                 channels=3,
+                 log_every_t=100,
+                 clip_denoised=True,
+                 linear_start=1e-4,
+                 linear_end=2e-2,
+                 cosine_s=8e-3,
+                 given_betas=None,
+                 original_elbo_weight=0.,
+                 v_posterior=0.,  # weight for choosing posterior variance as sigma = (1-v) * beta_tilde + v * beta
+                 l_simple_weight=1.,
+                 conditioning_key=None,
+                 parameterization="eps",  # all assuming fixed variance schedules
+                 scheduler_config=None,
+                 use_positional_encodings=False,
+                 learn_logvar=False,
+                 logvar_init=0.,
+                 ):
+        super().__init__()
+        assert parameterization in ["eps", "x0"], 'currently only supporting "eps" and "x0"'
+        self.parameterization = parameterization
+        print(f"{self.__class__.__name__}: Running in {self.parameterization}-prediction mode")
+        self.cond_stage_model = None
+        self.clip_denoised = clip_denoised
+        self.log_every_t = log_every_t
+        self.first_stage_key = first_stage_key
+        self.image_size = image_size  # try conv?
+        self.channels = channels
+        self.use_positional_encodings = use_positional_encodings
+        self.model = DiffusionWrapperV1(unet_config, conditioning_key)
+        count_params(self.model, verbose=True)
+        self.use_ema = use_ema
+        if self.use_ema:
+            self.model_ema = LitEma(self.model)
+            print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+        self.use_scheduler = scheduler_config is not None
+        if self.use_scheduler:
+            self.scheduler_config = scheduler_config
+
+        self.v_posterior = v_posterior
+        self.original_elbo_weight = original_elbo_weight
+        self.l_simple_weight = l_simple_weight
+
+        if monitor is not None:
+            self.monitor = monitor
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+
+        self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
+                               linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
+
+        self.loss_type = loss_type
+
+        self.learn_logvar = learn_logvar
+        self.logvar = torch.full(fill_value=logvar_init, size=(self.num_timesteps,))
+        if self.learn_logvar:
+            self.logvar = nn.Parameter(self.logvar, requires_grad=True)
+
+
+    def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000,
+                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+        if exists(given_betas):
+            betas = given_betas
+        else:
+            betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end,
+                                       cosine_s=cosine_s)
+        alphas = 1. - betas
+        alphas_cumprod = np.cumprod(alphas, axis=0)
+        alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])
+
+        timesteps, = betas.shape
+        self.num_timesteps = int(timesteps)
+        self.linear_start = linear_start
+        self.linear_end = linear_end
+        assert alphas_cumprod.shape[0] == self.num_timesteps, 'alphas have to be defined for each timestep'
+
+        to_torch = partial(torch.tensor, dtype=torch.float32)
+
+        self.register_buffer('betas', to_torch(betas))
+        self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+        self.register_buffer('alphas_cumprod_prev', to_torch(alphas_cumprod_prev))
+
+        # calculations for diffusion q(x_t | x_{t-1}) and others
+        self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod)))
+        self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod)))
+        self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod)))
+        self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod)))
+        self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod - 1)))
+
+        # calculations for posterior q(x_{t-1} | x_t, x_0)
+        posterior_variance = (1 - self.v_posterior) * betas * (1. - alphas_cumprod_prev) / (
+                    1. - alphas_cumprod) + self.v_posterior * betas
+        # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
+        self.register_buffer('posterior_variance', to_torch(posterior_variance))
+        # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
+        self.register_buffer('posterior_log_variance_clipped', to_torch(np.log(np.maximum(posterior_variance, 1e-20))))
+        self.register_buffer('posterior_mean_coef1', to_torch(
+            betas * np.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod)))
+        self.register_buffer('posterior_mean_coef2', to_torch(
+            (1. - alphas_cumprod_prev) * np.sqrt(alphas) / (1. - alphas_cumprod)))
+
+        if self.parameterization == "eps":
+            lvlb_weights = self.betas ** 2 / (
+                        2 * self.posterior_variance * to_torch(alphas) * (1 - self.alphas_cumprod))
+        elif self.parameterization == "x0":
+            lvlb_weights = 0.5 * np.sqrt(torch.Tensor(alphas_cumprod)) / (2. * 1 - torch.Tensor(alphas_cumprod))
+        else:
+            raise NotImplementedError("mu not supported")
+        # TODO how to choose this term
+        lvlb_weights[0] = lvlb_weights[1]
+        self.register_buffer('lvlb_weights', lvlb_weights, persistent=False)
+        assert not torch.isnan(self.lvlb_weights).all()
+
+    @contextmanager
+    def ema_scope(self, context=None):
+        if self.use_ema:
+            self.model_ema.store(self.model.parameters())
+            self.model_ema.copy_to(self.model)
+            if context is not None:
+                print(f"{context}: Switched to EMA weights")
+        try:
+            yield None
+        finally:
+            if self.use_ema:
+                self.model_ema.restore(self.model.parameters())
+                if context is not None:
+                    print(f"{context}: Restored training weights")
+
+    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+        sd = torch.load(path, map_location="cpu")
+        if "state_dict" in list(sd.keys()):
+            sd = sd["state_dict"]
+        keys = list(sd.keys())
+        for k in keys:
+            for ik in ignore_keys:
+                if k.startswith(ik):
+                    print("Deleting key {} from state_dict.".format(k))
+                    del sd[k]
+        missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
+            sd, strict=False)
+        print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
+        if len(missing) > 0:
+            print(f"Missing Keys: {missing}")
+        if len(unexpected) > 0:
+            print(f"Unexpected Keys: {unexpected}")
+
+    def q_mean_variance(self, x_start, t):
+        """
+        Get the distribution q(x_t | x_0).
+        :param x_start: the [N x C x ...] tensor of noiseless inputs.
+        :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
+        :return: A tuple (mean, variance, log_variance), all of x_start's shape.
+        """
+        mean = (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start)
+        variance = extract_into_tensor(1.0 - self.alphas_cumprod, t, x_start.shape)
+        log_variance = extract_into_tensor(self.log_one_minus_alphas_cumprod, t, x_start.shape)
+        return mean, variance, log_variance
+
+    def predict_start_from_noise(self, x_t, t, noise):
+        return (
+                extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t -
+                extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
+        )
+
+    def q_posterior(self, x_start, x_t, t):
+        posterior_mean = (
+                extract_into_tensor(self.posterior_mean_coef1, t, x_t.shape) * x_start +
+                extract_into_tensor(self.posterior_mean_coef2, t, x_t.shape) * x_t
+        )
+        posterior_variance = extract_into_tensor(self.posterior_variance, t, x_t.shape)
+        posterior_log_variance_clipped = extract_into_tensor(self.posterior_log_variance_clipped, t, x_t.shape)
+        return posterior_mean, posterior_variance, posterior_log_variance_clipped
+
+    def p_mean_variance(self, x, t, clip_denoised: bool):
+        model_out = self.model(x, t)
+        if self.parameterization == "eps":
+            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+        elif self.parameterization == "x0":
+            x_recon = model_out
+        if clip_denoised:
+            x_recon.clamp_(-1., 1.)
+
+        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        return model_mean, posterior_variance, posterior_log_variance
+
+    @torch.no_grad()
+    def p_sample(self, x, t, clip_denoised=True, repeat_noise=False):
+        b, *_, device = *x.shape, x.device
+        model_mean, _, model_log_variance = self.p_mean_variance(x=x, t=t, clip_denoised=clip_denoised)
+        noise = noise_like(x.shape, device, repeat_noise)
+        # no noise when t == 0
+        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+        return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+    @torch.no_grad()
+    def p_sample_loop(self, shape, return_intermediates=False):
+        device = self.betas.device
+        b = shape[0]
+        img = torch.randn(shape, device=device)
+        intermediates = [img]
+        for i in tqdm(reversed(range(0, self.num_timesteps)), desc='Sampling t', total=self.num_timesteps):
+            img = self.p_sample(img, torch.full((b,), i, device=device, dtype=torch.long),
+                                clip_denoised=self.clip_denoised)
+            if i % self.log_every_t == 0 or i == self.num_timesteps - 1:
+                intermediates.append(img)
+        if return_intermediates:
+            return img, intermediates
+        return img
+
+    @torch.no_grad()
+    def sample(self, batch_size=16, return_intermediates=False):
+        image_size = self.image_size
+        channels = self.channels
+        return self.p_sample_loop((batch_size, channels, image_size, image_size),
+                                  return_intermediates=return_intermediates)
+
+    def q_sample(self, x_start, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
+                extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)
+
+    def get_loss(self, pred, target, mean=True):
+        if self.loss_type == 'l1':
+            loss = (target - pred).abs()
+            if mean:
+                loss = loss.mean()
+        elif self.loss_type == 'l2':
+            if mean:
+                loss = torch.nn.functional.mse_loss(target, pred)
+            else:
+                loss = torch.nn.functional.mse_loss(target, pred, reduction='none')
+        else:
+            raise NotImplementedError("unknown loss type '{loss_type}'")
+
+        return loss
+
+    def p_losses(self, x_start, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+        model_out = self.model(x_noisy, t)
+
+        loss_dict = {}
+        if self.parameterization == "eps":
+            target = noise
+        elif self.parameterization == "x0":
+            target = x_start
+        else:
+            raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+
+        loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
+
+        log_prefix = 'train' if self.training else 'val'
+
+        loss_dict.update({f'{log_prefix}/loss_simple': loss.mean()})
+        loss_simple = loss.mean() * self.l_simple_weight
+
+        loss_vlb = (self.lvlb_weights[t] * loss).mean()
+        loss_dict.update({f'{log_prefix}/loss_vlb': loss_vlb})
+
+        loss = loss_simple + self.original_elbo_weight * loss_vlb
+
+        loss_dict.update({f'{log_prefix}/loss': loss})
+
+        return loss, loss_dict
+
+    def forward(self, x, *args, **kwargs):
+        # b, c, h, w, device, img_size, = *x.shape, x.device, self.image_size
+        # assert h == img_size and w == img_size, f'height and width of image must be {img_size}'
+        t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+        return self.p_losses(x, t, *args, **kwargs)
+
+    def get_input(self, batch, k):
+        x = batch[k]
+        if len(x.shape) == 3:
+            x = x[..., None]
+        x = rearrange(x, 'b h w c -> b c h w')
+        x = x.to(memory_format=torch.contiguous_format).float()
+        return x
+
+    def shared_step(self, batch):
+        x = self.get_input(batch, self.first_stage_key)
+        loss, loss_dict = self(x)
+        return loss, loss_dict
+
+    def training_step(self, batch, batch_idx):
+        loss, loss_dict = self.shared_step(batch)
+
+        self.log_dict(loss_dict, prog_bar=True,
+                      logger=True, on_step=True, on_epoch=True)
+
+        self.log("global_step", self.global_step,
+                 prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+        if self.use_scheduler:
+            lr = self.optimizers().param_groups[0]['lr']
+            self.log('lr_abs', lr, prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+        return loss
+
+    @torch.no_grad()
+    def validation_step(self, batch, batch_idx):
+        _, loss_dict_no_ema = self.shared_step(batch)
+        with self.ema_scope():
+            _, loss_dict_ema = self.shared_step(batch)
+            loss_dict_ema = {key + '_ema': loss_dict_ema[key] for key in loss_dict_ema}
+        self.log_dict(loss_dict_no_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+        self.log_dict(loss_dict_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+
+    def on_train_batch_end(self, *args, **kwargs):
+        if self.use_ema:
+            self.model_ema(self.model)
+
+    def _get_rows_from_list(self, samples):
+        n_imgs_per_row = len(samples)
+        denoise_grid = rearrange(samples, 'n b c h w -> b n c h w')
+        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+        return denoise_grid
+
+    @torch.no_grad()
+    def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
+        log = dict()
+        x = self.get_input(batch, self.first_stage_key)
+        N = min(x.shape[0], N)
+        n_row = min(x.shape[0], n_row)
+        x = x.to(self.device)[:N]
+        log["inputs"] = x
+
+        # get diffusion row
+        diffusion_row = list()
+        x_start = x[:n_row]
+
+        for t in range(self.num_timesteps):
+            if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+                t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+                t = t.to(self.device).long()
+                noise = torch.randn_like(x_start)
+                x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+                diffusion_row.append(x_noisy)
+
+        log["diffusion_row"] = self._get_rows_from_list(diffusion_row)
+
+        if sample:
+            # get denoise row
+            with self.ema_scope("Plotting"):
+                samples, denoise_row = self.sample(batch_size=N, return_intermediates=True)
+
+            log["samples"] = samples
+            log["denoise_row"] = self._get_rows_from_list(denoise_row)
+
+        if return_keys:
+            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+                return log
+            else:
+                return {key: log[key] for key in return_keys}
+        return log
+
+    def configure_optimizers(self):
+        lr = self.learning_rate
+        params = list(self.model.parameters())
+        if self.learn_logvar:
+            params = params + [self.logvar]
+        opt = torch.optim.AdamW(params, lr=lr)
+        return opt
+
+
+class LatentDiffusionV1(DDPMV1):
+    """main class"""
+    def __init__(self,
+                 first_stage_config,
+                 cond_stage_config,
+                 num_timesteps_cond=None,
+                 cond_stage_key="image",
+                 cond_stage_trainable=False,
+                 concat_mode=True,
+                 cond_stage_forward=None,
+                 conditioning_key=None,
+                 scale_factor=1.0,
+                 scale_by_std=False,
+                 *args, **kwargs):
+        self.num_timesteps_cond = default(num_timesteps_cond, 1)
+        self.scale_by_std = scale_by_std
+        assert self.num_timesteps_cond <= kwargs['timesteps']
+        # for backwards compatibility after implementation of DiffusionWrapper
+        if conditioning_key is None:
+            conditioning_key = 'concat' if concat_mode else 'crossattn'
+        if cond_stage_config == '__is_unconditional__':
+            conditioning_key = None
+        ckpt_path = kwargs.pop("ckpt_path", None)
+        ignore_keys = kwargs.pop("ignore_keys", [])
+        super().__init__(conditioning_key=conditioning_key, *args, **kwargs)
+        self.concat_mode = concat_mode
+        self.cond_stage_trainable = cond_stage_trainable
+        self.cond_stage_key = cond_stage_key
+        try:
+            self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
+        except:
+            self.num_downs = 0
+        if not scale_by_std:
+            self.scale_factor = scale_factor
+        else:
+            self.register_buffer('scale_factor', torch.tensor(scale_factor))
+        self.instantiate_first_stage(first_stage_config)
+        self.instantiate_cond_stage(cond_stage_config)
+        self.cond_stage_forward = cond_stage_forward
+        self.clip_denoised = False
+        self.bbox_tokenizer = None  
+
+        self.restarted_from_ckpt = False
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys)
+            self.restarted_from_ckpt = True
+
+    def make_cond_schedule(self, ):
+        self.cond_ids = torch.full(size=(self.num_timesteps,), fill_value=self.num_timesteps - 1, dtype=torch.long)
+        ids = torch.round(torch.linspace(0, self.num_timesteps - 1, self.num_timesteps_cond)).long()
+        self.cond_ids[:self.num_timesteps_cond] = ids
+
+    @rank_zero_only
+    @torch.no_grad()
+    def on_train_batch_start(self, batch, batch_idx, dataloader_idx):
+        # only for very first batch
+        if self.scale_by_std and self.current_epoch == 0 and self.global_step == 0 and batch_idx == 0 and not self.restarted_from_ckpt:
+            assert self.scale_factor == 1., 'rather not use custom rescaling and std-rescaling simultaneously'
+            # set rescale weight to 1./std of encodings
+            print("### USING STD-RESCALING ###")
+            x = super().get_input(batch, self.first_stage_key)
+            x = x.to(self.device)
+            encoder_posterior = self.encode_first_stage(x)
+            z = self.get_first_stage_encoding(encoder_posterior).detach()
+            del self.scale_factor
+            self.register_buffer('scale_factor', 1. / z.flatten().std())
+            print(f"setting self.scale_factor to {self.scale_factor}")
+            print("### USING STD-RESCALING ###")
+
+    def register_schedule(self,
+                          given_betas=None, beta_schedule="linear", timesteps=1000,
+                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+        super().register_schedule(given_betas, beta_schedule, timesteps, linear_start, linear_end, cosine_s)
+
+        self.shorten_cond_schedule = self.num_timesteps_cond > 1
+        if self.shorten_cond_schedule:
+            self.make_cond_schedule()
+
+    def instantiate_first_stage(self, config):
+        model = instantiate_from_config(config)
+        self.first_stage_model = model.eval()
+        self.first_stage_model.train = disabled_train
+        for param in self.first_stage_model.parameters():
+            param.requires_grad = False
+
+    def instantiate_cond_stage(self, config):
+        if not self.cond_stage_trainable:
+            if config == "__is_first_stage__":
+                print("Using first stage also as cond stage.")
+                self.cond_stage_model = self.first_stage_model
+            elif config == "__is_unconditional__":
+                print(f"Training {self.__class__.__name__} as an unconditional model.")
+                self.cond_stage_model = None
+                # self.be_unconditional = True
+            else:
+                model = instantiate_from_config(config)
+                self.cond_stage_model = model.eval()
+                self.cond_stage_model.train = disabled_train
+                for param in self.cond_stage_model.parameters():
+                    param.requires_grad = False
+        else:
+            assert config != '__is_first_stage__'
+            assert config != '__is_unconditional__'
+            model = instantiate_from_config(config)
+            self.cond_stage_model = model
+
+    def _get_denoise_row_from_list(self, samples, desc='', force_no_decoder_quantization=False):
+        denoise_row = []
+        for zd in tqdm(samples, desc=desc):
+            denoise_row.append(self.decode_first_stage(zd.to(self.device),
+                                                            force_not_quantize=force_no_decoder_quantization))
+        n_imgs_per_row = len(denoise_row)
+        denoise_row = torch.stack(denoise_row)  # n_log_step, n_row, C, H, W
+        denoise_grid = rearrange(denoise_row, 'n b c h w -> b n c h w')
+        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+        return denoise_grid
+
+    def get_first_stage_encoding(self, encoder_posterior):
+        if isinstance(encoder_posterior, DiagonalGaussianDistribution):
+            z = encoder_posterior.sample()
+        elif isinstance(encoder_posterior, torch.Tensor):
+            z = encoder_posterior
+        else:
+            raise NotImplementedError(f"encoder_posterior of type '{type(encoder_posterior)}' not yet implemented")
+        return self.scale_factor * z
+
+    def get_learned_conditioning(self, c):
+        if self.cond_stage_forward is None:
+            if hasattr(self.cond_stage_model, 'encode') and callable(self.cond_stage_model.encode):
+                c = self.cond_stage_model.encode(c)
+                if isinstance(c, DiagonalGaussianDistribution):
+                    c = c.mode()
+            else:
+                c = self.cond_stage_model(c)
+        else:
+            assert hasattr(self.cond_stage_model, self.cond_stage_forward)
+            c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
+        return c
+
+    def meshgrid(self, h, w):
+        y = torch.arange(0, h).view(h, 1, 1).repeat(1, w, 1)
+        x = torch.arange(0, w).view(1, w, 1).repeat(h, 1, 1)
+
+        arr = torch.cat([y, x], dim=-1)
+        return arr
+
+    def delta_border(self, h, w):
+        """
+        :param h: height
+        :param w: width
+        :return: normalized distance to image border,
+         wtith min distance = 0 at border and max dist = 0.5 at image center
+        """
+        lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
+        arr = self.meshgrid(h, w) / lower_right_corner
+        dist_left_up = torch.min(arr, dim=-1, keepdims=True)[0]
+        dist_right_down = torch.min(1 - arr, dim=-1, keepdims=True)[0]
+        edge_dist = torch.min(torch.cat([dist_left_up, dist_right_down], dim=-1), dim=-1)[0]
+        return edge_dist
+
+    def get_weighting(self, h, w, Ly, Lx, device):
+        weighting = self.delta_border(h, w)
+        weighting = torch.clip(weighting, self.split_input_params["clip_min_weight"],
+                               self.split_input_params["clip_max_weight"], )
+        weighting = weighting.view(1, h * w, 1).repeat(1, 1, Ly * Lx).to(device)
+
+        if self.split_input_params["tie_braker"]:
+            L_weighting = self.delta_border(Ly, Lx)
+            L_weighting = torch.clip(L_weighting,
+                                     self.split_input_params["clip_min_tie_weight"],
+                                     self.split_input_params["clip_max_tie_weight"])
+
+            L_weighting = L_weighting.view(1, 1, Ly * Lx).to(device)
+            weighting = weighting * L_weighting
+        return weighting
+
+    def get_fold_unfold(self, x, kernel_size, stride, uf=1, df=1):  # todo load once not every time, shorten code
+        """
+        :param x: img of size (bs, c, h, w)
+        :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
+        """
+        bs, nc, h, w = x.shape
+
+        # number of crops in image
+        Ly = (h - kernel_size[0]) // stride[0] + 1
+        Lx = (w - kernel_size[1]) // stride[1] + 1
+
+        if uf == 1 and df == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold = torch.nn.Fold(output_size=x.shape[2:], **fold_params)
+
+            weighting = self.get_weighting(kernel_size[0], kernel_size[1], Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h, w)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0], kernel_size[1], Ly * Lx))
+
+        elif uf > 1 and df == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold_params2 = dict(kernel_size=(kernel_size[0] * uf, kernel_size[0] * uf),
+                                dilation=1, padding=0,
+                                stride=(stride[0] * uf, stride[1] * uf))
+            fold = torch.nn.Fold(output_size=(x.shape[2] * uf, x.shape[3] * uf), **fold_params2)
+
+            weighting = self.get_weighting(kernel_size[0] * uf, kernel_size[1] * uf, Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h * uf, w * uf)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0] * uf, kernel_size[1] * uf, Ly * Lx))
+
+        elif df > 1 and uf == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold_params2 = dict(kernel_size=(kernel_size[0] // df, kernel_size[0] // df),
+                                dilation=1, padding=0,
+                                stride=(stride[0] // df, stride[1] // df))
+            fold = torch.nn.Fold(output_size=(x.shape[2] // df, x.shape[3] // df), **fold_params2)
+
+            weighting = self.get_weighting(kernel_size[0] // df, kernel_size[1] // df, Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h // df, w // df)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0] // df, kernel_size[1] // df, Ly * Lx))
+
+        else:
+            raise NotImplementedError
+
+        return fold, unfold, normalization, weighting
+
+    @torch.no_grad()
+    def get_input(self, batch, k, return_first_stage_outputs=False, force_c_encode=False,
+                  cond_key=None, return_original_cond=False, bs=None):
+        x = super().get_input(batch, k)
+        if bs is not None:
+            x = x[:bs]
+        x = x.to(self.device)
+        encoder_posterior = self.encode_first_stage(x)
+        z = self.get_first_stage_encoding(encoder_posterior).detach()
+
+        if self.model.conditioning_key is not None:
+            if cond_key is None:
+                cond_key = self.cond_stage_key
+            if cond_key != self.first_stage_key:
+                if cond_key in ['caption', 'coordinates_bbox']:
+                    xc = batch[cond_key]
+                elif cond_key == 'class_label':
+                    xc = batch
+                else:
+                    xc = super().get_input(batch, cond_key).to(self.device)
+            else:
+                xc = x
+            if not self.cond_stage_trainable or force_c_encode:
+                if isinstance(xc, dict) or isinstance(xc, list):
+                    # import pudb; pudb.set_trace()
+                    c = self.get_learned_conditioning(xc)
+                else:
+                    c = self.get_learned_conditioning(xc.to(self.device))
+            else:
+                c = xc
+            if bs is not None:
+                c = c[:bs]
+
+            if self.use_positional_encodings:
+                pos_x, pos_y = self.compute_latent_shifts(batch)
+                ckey = __conditioning_keys__[self.model.conditioning_key]
+                c = {ckey: c, 'pos_x': pos_x, 'pos_y': pos_y}
+
+        else:
+            c = None
+            xc = None
+            if self.use_positional_encodings:
+                pos_x, pos_y = self.compute_latent_shifts(batch)
+                c = {'pos_x': pos_x, 'pos_y': pos_y}
+        out = [z, c]
+        if return_first_stage_outputs:
+            xrec = self.decode_first_stage(z)
+            out.extend([x, xrec])
+        if return_original_cond:
+            out.append(xc)
+        return out
+
+    @torch.no_grad()
+    def decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+        if predict_cids:
+            if z.dim() == 4:
+                z = torch.argmax(z.exp(), dim=1).long()
+            z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+            z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+        z = 1. / self.scale_factor * z
+
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                uf = self.split_input_params["vqf"]
+                bs, nc, h, w = z.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+                z = unfold(z)  # (bn, nc * prod(**ks), L)
+                # 1. Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                # 2. apply model loop over last dim
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+                                                                 force_not_quantize=predict_cids or force_not_quantize)
+                                   for i in range(z.shape[-1])]
+                else:
+
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+                                   for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)  # # (bn, nc, ks[0], ks[1], L)
+                o = o * weighting
+                # Reverse 1. reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization  # norm is shape (1, 1, h, w)
+                return decoded
+            else:
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+                else:
+                    return self.first_stage_model.decode(z)
+
+        else:
+            if isinstance(self.first_stage_model, VQModelInterface):
+                return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+            else:
+                return self.first_stage_model.decode(z)
+
+    # same as above but without decorator
+    def differentiable_decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+        if predict_cids:
+            if z.dim() == 4:
+                z = torch.argmax(z.exp(), dim=1).long()
+            z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+            z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+        z = 1. / self.scale_factor * z
+
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                uf = self.split_input_params["vqf"]
+                bs, nc, h, w = z.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+                z = unfold(z)  # (bn, nc * prod(**ks), L)
+                # 1. Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                # 2. apply model loop over last dim
+                if isinstance(self.first_stage_model, VQModelInterface):  
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+                                                                 force_not_quantize=predict_cids or force_not_quantize)
+                                   for i in range(z.shape[-1])]
+                else:
+
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+                                   for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)  # # (bn, nc, ks[0], ks[1], L)
+                o = o * weighting
+                # Reverse 1. reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization  # norm is shape (1, 1, h, w)
+                return decoded
+            else:
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+                else:
+                    return self.first_stage_model.decode(z)
+
+        else:
+            if isinstance(self.first_stage_model, VQModelInterface):
+                return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+            else:
+                return self.first_stage_model.decode(z)
+
+    @torch.no_grad()
+    def encode_first_stage(self, x):
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                df = self.split_input_params["vqf"]
+                self.split_input_params['original_image_size'] = x.shape[-2:]
+                bs, nc, h, w = x.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(x, ks, stride, df=df)
+                z = unfold(x)  # (bn, nc * prod(**ks), L)
+                # Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                output_list = [self.first_stage_model.encode(z[:, :, :, :, i])
+                               for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)
+                o = o * weighting
+
+                # Reverse reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization
+                return decoded
+
+            else:
+                return self.first_stage_model.encode(x)
+        else:
+            return self.first_stage_model.encode(x)
+
+    def shared_step(self, batch, **kwargs):
+        x, c = self.get_input(batch, self.first_stage_key)
+        loss = self(x, c)
+        return loss
+
+    def forward(self, x, c, *args, **kwargs):
+        t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+        if self.model.conditioning_key is not None:
+            assert c is not None
+            if self.cond_stage_trainable:
+                c = self.get_learned_conditioning(c)
+            if self.shorten_cond_schedule:  # TODO: drop this option
+                tc = self.cond_ids[t].to(self.device)
+                c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
+        return self.p_losses(x, c, t, *args, **kwargs)
+
+    def _rescale_annotations(self, bboxes, crop_coordinates):  # TODO: move to dataset
+        def rescale_bbox(bbox):
+            x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
+            y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
+            w = min(bbox[2] / crop_coordinates[2], 1 - x0)
+            h = min(bbox[3] / crop_coordinates[3], 1 - y0)
+            return x0, y0, w, h
+
+        return [rescale_bbox(b) for b in bboxes]
+
+    def apply_model(self, x_noisy, t, cond, return_ids=False):
+
+        if isinstance(cond, dict):
+            # hybrid case, cond is exptected to be a dict
+            pass
+        else:
+            if not isinstance(cond, list):
+                cond = [cond]
+            key = 'c_concat' if self.model.conditioning_key == 'concat' else 'c_crossattn'
+            cond = {key: cond}
+
+        if hasattr(self, "split_input_params"):
+            assert len(cond) == 1  # todo can only deal with one conditioning atm
+            assert not return_ids  
+            ks = self.split_input_params["ks"]  # eg. (128, 128)
+            stride = self.split_input_params["stride"]  # eg. (64, 64)
+
+            h, w = x_noisy.shape[-2:]
+
+            fold, unfold, normalization, weighting = self.get_fold_unfold(x_noisy, ks, stride)
+
+            z = unfold(x_noisy)  # (bn, nc * prod(**ks), L)
+            # Reshape to img shape
+            z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+            z_list = [z[:, :, :, :, i] for i in range(z.shape[-1])]
+
+            if self.cond_stage_key in ["image", "LR_image", "segmentation",
+                                       'bbox_img'] and self.model.conditioning_key:  # todo check for completeness
+                c_key = next(iter(cond.keys()))  # get key
+                c = next(iter(cond.values()))  # get value
+                assert (len(c) == 1)  # todo extend to list with more than one elem
+                c = c[0]  # get element
+
+                c = unfold(c)
+                c = c.view((c.shape[0], -1, ks[0], ks[1], c.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
+
+            elif self.cond_stage_key == 'coordinates_bbox':
+                assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+
+                # assuming padding of unfold is always 0 and its dilation is always 1
+                n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
+                full_img_h, full_img_w = self.split_input_params['original_image_size']
+                # as we are operating on latents, we need the factor from the original image size to the
+                # spatial latent size to properly rescale the crops for regenerating the bbox annotations
+                num_downs = self.first_stage_model.encoder.num_resolutions - 1
+                rescale_latent = 2 ** (num_downs)
+
+                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+                # need to rescale the tl patch coordinates to be in between (0,1)
+                tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
+                                         rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)
+                                        for patch_nr in range(z.shape[-1])]
+
+                # patch_limits are tl_coord, width and height coordinates as (x_tl, y_tl, h, w)
+                patch_limits = [(x_tl, y_tl,
+                                 rescale_latent * ks[0] / full_img_w,
+                                 rescale_latent * ks[1] / full_img_h) for x_tl, y_tl in tl_patch_coordinates]
+                # patch_values = [(np.arange(x_tl,min(x_tl+ks, 1.)),np.arange(y_tl,min(y_tl+ks, 1.))) for x_tl, y_tl in tl_patch_coordinates]
+
+                # tokenize crop coordinates for the bounding boxes of the respective patches
+                patch_limits_tknzd = [torch.LongTensor(self.bbox_tokenizer._crop_encoder(bbox))[None].to(self.device)
+                                      for bbox in patch_limits]  # list of length l with tensors of shape (1, 2)
+                print(patch_limits_tknzd[0].shape)
+                # cut tknzd crop position from conditioning
+                assert isinstance(cond, dict), 'cond must be dict to be fed into model'
+                cut_cond = cond['c_crossattn'][0][..., :-2].to(self.device)
+                print(cut_cond.shape)
+
+                adapted_cond = torch.stack([torch.cat([cut_cond, p], dim=1) for p in patch_limits_tknzd])
+                adapted_cond = rearrange(adapted_cond, 'l b n -> (l b) n')
+                print(adapted_cond.shape)
+                adapted_cond = self.get_learned_conditioning(adapted_cond)
+                print(adapted_cond.shape)
+                adapted_cond = rearrange(adapted_cond, '(l b) n d -> l b n d', l=z.shape[-1])
+                print(adapted_cond.shape)
+
+                cond_list = [{'c_crossattn': [e]} for e in adapted_cond]
+
+            else:
+                cond_list = [cond for i in range(z.shape[-1])]  # Todo make this more efficient
+
+            # apply model by loop over crops
+            output_list = [self.model(z_list[i], t, **cond_list[i]) for i in range(z.shape[-1])]
+            assert not isinstance(output_list[0],
+                                  tuple)  # todo cant deal with multiple model outputs check this never happens
+
+            o = torch.stack(output_list, axis=-1)
+            o = o * weighting
+            # Reverse reshape to img shape
+            o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+            # stitch crops together
+            x_recon = fold(o) / normalization
+
+        else:
+            x_recon = self.model(x_noisy, t, **cond)
+
+        if isinstance(x_recon, tuple) and not return_ids:
+            return x_recon[0]
+        else:
+            return x_recon
+
+    def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
+        return (extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t - pred_xstart) / \
+               extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)
+
+    def _prior_bpd(self, x_start):
+        """
+        Get the prior KL term for the variational lower-bound, measured in
+        bits-per-dim.
+        This term can't be optimized, as it only depends on the encoder.
+        :param x_start: the [N x C x ...] tensor of inputs.
+        :return: a batch of [N] KL values (in bits), one per batch element.
+        """
+        batch_size = x_start.shape[0]
+        t = torch.tensor([self.num_timesteps - 1] * batch_size, device=x_start.device)
+        qt_mean, _, qt_log_variance = self.q_mean_variance(x_start, t)
+        kl_prior = normal_kl(mean1=qt_mean, logvar1=qt_log_variance, mean2=0.0, logvar2=0.0)
+        return mean_flat(kl_prior) / np.log(2.0)
+
+    def p_losses(self, x_start, cond, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+        model_output = self.apply_model(x_noisy, t, cond)
+
+        loss_dict = {}
+        prefix = 'train' if self.training else 'val'
+
+        if self.parameterization == "x0":
+            target = x_start
+        elif self.parameterization == "eps":
+            target = noise
+        else:
+            raise NotImplementedError()
+
+        loss_simple = self.get_loss(model_output, target, mean=False).mean([1, 2, 3])
+        loss_dict.update({f'{prefix}/loss_simple': loss_simple.mean()})
+
+        logvar_t = self.logvar[t].to(self.device)
+        loss = loss_simple / torch.exp(logvar_t) + logvar_t
+        # loss = loss_simple / torch.exp(self.logvar) + self.logvar
+        if self.learn_logvar:
+            loss_dict.update({f'{prefix}/loss_gamma': loss.mean()})
+            loss_dict.update({'logvar': self.logvar.data.mean()})
+
+        loss = self.l_simple_weight * loss.mean()
+
+        loss_vlb = self.get_loss(model_output, target, mean=False).mean(dim=(1, 2, 3))
+        loss_vlb = (self.lvlb_weights[t] * loss_vlb).mean()
+        loss_dict.update({f'{prefix}/loss_vlb': loss_vlb})
+        loss += (self.original_elbo_weight * loss_vlb)
+        loss_dict.update({f'{prefix}/loss': loss})
+
+        return loss, loss_dict
+
+    def p_mean_variance(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
+                        return_x0=False, score_corrector=None, corrector_kwargs=None):
+        t_in = t
+        model_out = self.apply_model(x, t_in, c, return_ids=return_codebook_ids)
+
+        if score_corrector is not None:
+            assert self.parameterization == "eps"
+            model_out = score_corrector.modify_score(self, model_out, x, t, c, **corrector_kwargs)
+
+        if return_codebook_ids:
+            model_out, logits = model_out
+
+        if self.parameterization == "eps":
+            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+        elif self.parameterization == "x0":
+            x_recon = model_out
+        else:
+            raise NotImplementedError()
+
+        if clip_denoised:
+            x_recon.clamp_(-1., 1.)
+        if quantize_denoised:
+            x_recon, _, [_, _, indices] = self.first_stage_model.quantize(x_recon)
+        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        if return_codebook_ids:
+            return model_mean, posterior_variance, posterior_log_variance, logits
+        elif return_x0:
+            return model_mean, posterior_variance, posterior_log_variance, x_recon
+        else:
+            return model_mean, posterior_variance, posterior_log_variance
+
+    @torch.no_grad()
+    def p_sample(self, x, c, t, clip_denoised=False, repeat_noise=False,
+                 return_codebook_ids=False, quantize_denoised=False, return_x0=False,
+                 temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None):
+        b, *_, device = *x.shape, x.device
+        outputs = self.p_mean_variance(x=x, c=c, t=t, clip_denoised=clip_denoised,
+                                       return_codebook_ids=return_codebook_ids,
+                                       quantize_denoised=quantize_denoised,
+                                       return_x0=return_x0,
+                                       score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+        if return_codebook_ids:
+            raise DeprecationWarning("Support dropped.")
+            model_mean, _, model_log_variance, logits = outputs
+        elif return_x0:
+            model_mean, _, model_log_variance, x0 = outputs
+        else:
+            model_mean, _, model_log_variance = outputs
+
+        noise = noise_like(x.shape, device, repeat_noise) * temperature
+        if noise_dropout > 0.:
+            noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+        # no noise when t == 0
+        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+
+        if return_codebook_ids:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, logits.argmax(dim=1)
+        if return_x0:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, x0
+        else:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+    @torch.no_grad()
+    def progressive_denoising(self, cond, shape, verbose=True, callback=None, quantize_denoised=False,
+                              img_callback=None, mask=None, x0=None, temperature=1., noise_dropout=0.,
+                              score_corrector=None, corrector_kwargs=None, batch_size=None, x_T=None, start_T=None,
+                              log_every_t=None):
+        if not log_every_t:
+            log_every_t = self.log_every_t
+        timesteps = self.num_timesteps
+        if batch_size is not None:
+            b = batch_size if batch_size is not None else shape[0]
+            shape = [batch_size] + list(shape)
+        else:
+            b = batch_size = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=self.device)
+        else:
+            img = x_T
+        intermediates = []
+        if cond is not None:
+            if isinstance(cond, dict):
+                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+            else:
+                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+
+        if start_T is not None:
+            timesteps = min(timesteps, start_T)
+        iterator = tqdm(reversed(range(0, timesteps)), desc='Progressive Generation',
+                        total=timesteps) if verbose else reversed(
+            range(0, timesteps))
+        if type(temperature) == float:
+            temperature = [temperature] * timesteps
+
+        for i in iterator:
+            ts = torch.full((b,), i, device=self.device, dtype=torch.long)
+            if self.shorten_cond_schedule:
+                assert self.model.conditioning_key != 'hybrid'
+                tc = self.cond_ids[ts].to(cond.device)
+                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+            img, x0_partial = self.p_sample(img, cond, ts,
+                                            clip_denoised=self.clip_denoised,
+                                            quantize_denoised=quantize_denoised, return_x0=True,
+                                            temperature=temperature[i], noise_dropout=noise_dropout,
+                                            score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+            if mask is not None:
+                assert x0 is not None
+                img_orig = self.q_sample(x0, ts)
+                img = img_orig * mask + (1. - mask) * img
+
+            if i % log_every_t == 0 or i == timesteps - 1:
+                intermediates.append(x0_partial)
+            if callback: callback(i)
+            if img_callback: img_callback(img, i)
+        return img, intermediates
+
+    @torch.no_grad()
+    def p_sample_loop(self, cond, shape, return_intermediates=False,
+                      x_T=None, verbose=True, callback=None, timesteps=None, quantize_denoised=False,
+                      mask=None, x0=None, img_callback=None, start_T=None,
+                      log_every_t=None):
+
+        if not log_every_t:
+            log_every_t = self.log_every_t
+        device = self.betas.device
+        b = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=device)
+        else:
+            img = x_T
+
+        intermediates = [img]
+        if timesteps is None:
+            timesteps = self.num_timesteps
+
+        if start_T is not None:
+            timesteps = min(timesteps, start_T)
+        iterator = tqdm(reversed(range(0, timesteps)), desc='Sampling t', total=timesteps) if verbose else reversed(
+            range(0, timesteps))
+
+        if mask is not None:
+            assert x0 is not None
+            assert x0.shape[2:3] == mask.shape[2:3]  # spatial size has to match
+
+        for i in iterator:
+            ts = torch.full((b,), i, device=device, dtype=torch.long)
+            if self.shorten_cond_schedule:
+                assert self.model.conditioning_key != 'hybrid'
+                tc = self.cond_ids[ts].to(cond.device)
+                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+            img = self.p_sample(img, cond, ts,
+                                clip_denoised=self.clip_denoised,
+                                quantize_denoised=quantize_denoised)
+            if mask is not None:
+                img_orig = self.q_sample(x0, ts)
+                img = img_orig * mask + (1. - mask) * img
+
+            if i % log_every_t == 0 or i == timesteps - 1:
+                intermediates.append(img)
+            if callback: callback(i)
+            if img_callback: img_callback(img, i)
+
+        if return_intermediates:
+            return img, intermediates
+        return img
+
+    @torch.no_grad()
+    def sample(self, cond, batch_size=16, return_intermediates=False, x_T=None,
+               verbose=True, timesteps=None, quantize_denoised=False,
+               mask=None, x0=None, shape=None,**kwargs):
+        if shape is None:
+            shape = (batch_size, self.channels, self.image_size, self.image_size)
+        if cond is not None:
+            if isinstance(cond, dict):
+                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+            else:
+                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+        return self.p_sample_loop(cond,
+                                  shape,
+                                  return_intermediates=return_intermediates, x_T=x_T,
+                                  verbose=verbose, timesteps=timesteps, quantize_denoised=quantize_denoised,
+                                  mask=mask, x0=x0)
+
+    @torch.no_grad()
+    def sample_log(self,cond,batch_size,ddim, ddim_steps,**kwargs):
+
+        if ddim:
+            ddim_sampler = DDIMSampler(self)
+            shape = (self.channels, self.image_size, self.image_size)
+            samples, intermediates =ddim_sampler.sample(ddim_steps,batch_size,
+                                                        shape,cond,verbose=False,**kwargs)
+
+        else:
+            samples, intermediates = self.sample(cond=cond, batch_size=batch_size,
+                                                 return_intermediates=True,**kwargs)
+
+        return samples, intermediates
+
+
+    @torch.no_grad()
+    def log_images(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
+                   quantize_denoised=True, inpaint=True, plot_denoise_rows=False, plot_progressive_rows=True,
+                   plot_diffusion_rows=True, **kwargs):
+
+        use_ddim = ddim_steps is not None
+
+        log = dict()
+        z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
+                                           return_first_stage_outputs=True,
+                                           force_c_encode=True,
+                                           return_original_cond=True,
+                                           bs=N)
+        N = min(x.shape[0], N)
+        n_row = min(x.shape[0], n_row)
+        log["inputs"] = x
+        log["reconstruction"] = xrec
+        if self.model.conditioning_key is not None:
+            if hasattr(self.cond_stage_model, "decode"):
+                xc = self.cond_stage_model.decode(c)
+                log["conditioning"] = xc
+            elif self.cond_stage_key in ["caption"]:
+                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["caption"])
+                log["conditioning"] = xc
+            elif self.cond_stage_key == 'class_label':
+                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"])
+                log['conditioning'] = xc
+            elif isimage(xc):
+                log["conditioning"] = xc
+            if ismap(xc):
+                log["original_conditioning"] = self.to_rgb(xc)
+
+        if plot_diffusion_rows:
+            # get diffusion row
+            diffusion_row = list()
+            z_start = z[:n_row]
+            for t in range(self.num_timesteps):
+                if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+                    t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+                    t = t.to(self.device).long()
+                    noise = torch.randn_like(z_start)
+                    z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
+                    diffusion_row.append(self.decode_first_stage(z_noisy))
+
+            diffusion_row = torch.stack(diffusion_row)  # n_log_step, n_row, C, H, W
+            diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
+            diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
+            diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
+            log["diffusion_row"] = diffusion_grid
+
+        if sample:
+            # get denoise row
+            with self.ema_scope("Plotting"):
+                samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+                                                         ddim_steps=ddim_steps,eta=ddim_eta)
+                # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
+            x_samples = self.decode_first_stage(samples)
+            log["samples"] = x_samples
+            if plot_denoise_rows:
+                denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
+                log["denoise_row"] = denoise_grid
+
+            if quantize_denoised and not isinstance(self.first_stage_model, AutoencoderKL) and not isinstance(
+                    self.first_stage_model, IdentityFirstStage):
+                # also display when quantizing x0 while sampling
+                with self.ema_scope("Plotting Quantized Denoised"):
+                    samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+                                                             ddim_steps=ddim_steps,eta=ddim_eta,
+                                                             quantize_denoised=True)
+                    # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True,
+                    #                                      quantize_denoised=True)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_x0_quantized"] = x_samples
+
+            if inpaint:
+                # make a simple center square
+                b, h, w = z.shape[0], z.shape[2], z.shape[3]
+                mask = torch.ones(N, h, w).to(self.device)
+                # zeros will be filled in
+                mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
+                mask = mask[:, None, ...]
+                with self.ema_scope("Plotting Inpaint"):
+
+                    samples, _ = self.sample_log(cond=c,batch_size=N,ddim=use_ddim, eta=ddim_eta,
+                                                ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_inpainting"] = x_samples
+                log["mask"] = mask
+
+                # outpaint
+                with self.ema_scope("Plotting Outpaint"):
+                    samples, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,eta=ddim_eta,
+                                                ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_outpainting"] = x_samples
+
+        if plot_progressive_rows:
+            with self.ema_scope("Plotting Progressives"):
+                img, progressives = self.progressive_denoising(c,
+                                                               shape=(self.channels, self.image_size, self.image_size),
+                                                               batch_size=N)
+            prog_row = self._get_denoise_row_from_list(progressives, desc="Progressive Generation")
+            log["progressive_row"] = prog_row
+
+        if return_keys:
+            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+                return log
+            else:
+                return {key: log[key] for key in return_keys}
+        return log
+
+    def configure_optimizers(self):
+        lr = self.learning_rate
+        params = list(self.model.parameters())
+        if self.cond_stage_trainable:
+            print(f"{self.__class__.__name__}: Also optimizing conditioner params!")
+            params = params + list(self.cond_stage_model.parameters())
+        if self.learn_logvar:
+            print('Diffusion model optimizing logvar')
+            params.append(self.logvar)
+        opt = torch.optim.AdamW(params, lr=lr)
+        if self.use_scheduler:
+            assert 'target' in self.scheduler_config
+            scheduler = instantiate_from_config(self.scheduler_config)
+
+            print("Setting up LambdaLR scheduler...")
+            scheduler = [
+                {
+                    'scheduler': LambdaLR(opt, lr_lambda=scheduler.schedule),
+                    'interval': 'step',
+                    'frequency': 1
+                }]
+            return [opt], scheduler
+        return opt
+
+    @torch.no_grad()
+    def to_rgb(self, x):
+        x = x.float()
+        if not hasattr(self, "colorize"):
+            self.colorize = torch.randn(3, x.shape[1], 1, 1).to(x)
+        x = nn.functional.conv2d(x, weight=self.colorize)
+        x = 2. * (x - x.min()) / (x.max() - x.min()) - 1.
+        return x
+
+
+class DiffusionWrapperV1(pl.LightningModule):
+    def __init__(self, diff_model_config, conditioning_key):
+        super().__init__()
+        self.diffusion_model = instantiate_from_config(diff_model_config)
+        self.conditioning_key = conditioning_key
+        assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm']
+
+    def forward(self, x, t, c_concat: list = None, c_crossattn: list = None):
+        if self.conditioning_key is None:
+            out = self.diffusion_model(x, t)
+        elif self.conditioning_key == 'concat':
+            xc = torch.cat([x] + c_concat, dim=1)
+            out = self.diffusion_model(xc, t)
+        elif self.conditioning_key == 'crossattn':
+            cc = torch.cat(c_crossattn, 1)
+            out = self.diffusion_model(x, t, context=cc)
+        elif self.conditioning_key == 'hybrid':
+            xc = torch.cat([x] + c_concat, dim=1)
+            cc = torch.cat(c_crossattn, 1)
+            out = self.diffusion_model(xc, t, context=cc)
+        elif self.conditioning_key == 'adm':
+            cc = c_crossattn[0]
+            out = self.diffusion_model(x, t, y=cc)
+        else:
+            raise NotImplementedError()
+
+        return out
+
+
+class Layout2ImgDiffusionV1(LatentDiffusionV1):
+    # TODO: move all layout-specific hacks to this class
+    def __init__(self, cond_stage_key, *args, **kwargs):
+        assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
+        super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+
+    def log_images(self, batch, N=8, *args, **kwargs):
+        logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+
+        key = 'train' if self.training else 'validation'
+        dset = self.trainer.datamodule.datasets[key]
+        mapper = dset.conditional_builders[self.cond_stage_key]
+
+        bbox_imgs = []
+        map_fn = lambda catno: dset.get_textual_label(dset.get_category_id(catno))
+        for tknzd_bbox in batch[self.cond_stage_key][:N]:
+            bboximg = mapper.plot(tknzd_bbox.detach().cpu(), map_fn, (256, 256))
+            bbox_imgs.append(bboximg)
+
+        cond_img = torch.stack(bbox_imgs, dim=0)
+        logs['bbox_image'] = cond_img
+        return logs
+
+setattr(ldm.models.diffusion.ddpm, "DDPMV1", DDPMV1)
+setattr(ldm.models.diffusion.ddpm, "LatentDiffusionV1", LatentDiffusionV1)
+setattr(ldm.models.diffusion.ddpm, "DiffusionWrapperV1", DiffusionWrapperV1)
+setattr(ldm.models.diffusion.ddpm, "Layout2ImgDiffusionV1", Layout2ImgDiffusionV1)
diff --git a/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js b/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js
new file mode 100644
index 00000000..3f3bebcd
--- /dev/null
+++ b/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js
@@ -0,0 +1,107 @@
+// Stable Diffusion WebUI - Bracket checker
+// Version 1.0
+// By Hingashi no Florin/Bwin4L
+// Counts open and closed brackets (round, square, curly) in the prompt and negative prompt text boxes in the txt2img and img2img tabs.
+// If there's a mismatch, the keyword counter turns red and if you hover on it, a tooltip tells you what's wrong.
+
+function checkBrackets(evt) {
+  textArea = evt.target;
+  tabName = evt.target.parentElement.parentElement.id.split("_")[0];
+  counterElt = document.querySelector('gradio-app').shadowRoot.querySelector('#' + tabName + '_token_counter');
+
+  promptName = evt.target.parentElement.parentElement.id.includes('neg') ? ' negative' : '';
+
+  errorStringParen  = '(' + tabName + promptName + ' prompt) - Different number of opening and closing parentheses detected.\n';
+  errorStringSquare = '[' + tabName + promptName + ' prompt] - Different number of opening and closing square brackets detected.\n';
+  errorStringCurly  = '{' + tabName + promptName + ' prompt} - Different number of opening and closing curly brackets detected.\n';
+
+  openBracketRegExp = /\(/g;
+  closeBracketRegExp = /\)/g;
+
+  openSquareBracketRegExp = /\[/g;
+  closeSquareBracketRegExp = /\]/g;
+
+  openCurlyBracketRegExp = /\{/g;
+  closeCurlyBracketRegExp = /\}/g;
+
+  totalOpenBracketMatches = 0;
+  totalCloseBracketMatches = 0;
+  totalOpenSquareBracketMatches = 0;
+  totalCloseSquareBracketMatches = 0;
+  totalOpenCurlyBracketMatches = 0;
+  totalCloseCurlyBracketMatches = 0;
+
+  openBracketMatches = textArea.value.match(openBracketRegExp);
+  if(openBracketMatches) {
+    totalOpenBracketMatches = openBracketMatches.length;
+  }
+
+  closeBracketMatches = textArea.value.match(closeBracketRegExp);
+  if(closeBracketMatches) {
+    totalCloseBracketMatches = closeBracketMatches.length;
+  }
+
+  openSquareBracketMatches = textArea.value.match(openSquareBracketRegExp);
+  if(openSquareBracketMatches) {
+    totalOpenSquareBracketMatches = openSquareBracketMatches.length;
+  }
+
+  closeSquareBracketMatches = textArea.value.match(closeSquareBracketRegExp);
+  if(closeSquareBracketMatches) {
+    totalCloseSquareBracketMatches = closeSquareBracketMatches.length;
+  }
+
+  openCurlyBracketMatches = textArea.value.match(openCurlyBracketRegExp);
+  if(openCurlyBracketMatches) {
+    totalOpenCurlyBracketMatches = openCurlyBracketMatches.length;
+  }
+
+  closeCurlyBracketMatches = textArea.value.match(closeCurlyBracketRegExp);
+  if(closeCurlyBracketMatches) {
+    totalCloseCurlyBracketMatches = closeCurlyBracketMatches.length;
+  }
+
+  if(totalOpenBracketMatches != totalCloseBracketMatches) {
+    if(!counterElt.title.includes(errorStringParen)) {
+      counterElt.title += errorStringParen;
+    }
+  } else {
+    counterElt.title = counterElt.title.replace(errorStringParen, '');
+  }
+
+  if(totalOpenSquareBracketMatches != totalCloseSquareBracketMatches) {
+    if(!counterElt.title.includes(errorStringSquare)) {
+      counterElt.title += errorStringSquare;
+    }
+  } else {
+    counterElt.title = counterElt.title.replace(errorStringSquare, '');
+  }
+
+  if(totalOpenCurlyBracketMatches != totalCloseCurlyBracketMatches) {
+    if(!counterElt.title.includes(errorStringCurly)) {
+      counterElt.title += errorStringCurly;
+    }
+  } else {
+    counterElt.title = counterElt.title.replace(errorStringCurly, '');
+  }
+
+  if(counterElt.title != '') {
+    counterElt.style = 'color: #FF5555;';
+  } else {
+    counterElt.style = 'color: #000;';
+  }
+}
+
+var shadowRootLoaded = setInterval(function() {
+  var shadowTextArea = document.querySelector('gradio-app').shadowRoot.querySelectorAll('#txt2img_prompt > label > textarea');
+  if(shadowTextArea.length < 1) {
+      return false;
+  }
+
+  clearInterval(shadowRootLoaded);
+
+  document.querySelector('gradio-app').shadowRoot.querySelector('#txt2img_prompt').onkeyup = checkBrackets;
+  document.querySelector('gradio-app').shadowRoot.querySelector('#txt2img_neg_prompt').onkeyup = checkBrackets;
+  document.querySelector('gradio-app').shadowRoot.querySelector('#img2img_prompt').onkeyup = checkBrackets;
+  document.querySelector('gradio-app').shadowRoot.querySelector('#img2img_neg_prompt').onkeyup = checkBrackets;
+}, 1000);
diff --git a/javascript/hints.js b/javascript/hints.js
index 57db35be..47e24616 100644
--- a/javascript/hints.js
+++ b/javascript/hints.js
@@ -17,6 +17,7 @@ titles = {
     "\u2199\ufe0f": "Read generation parameters from prompt or last generation if prompt is empty into user interface.",
     "\u{1f4c2}": "Open images output directory",
     "\u{1f4be}": "Save style",
+    "\U0001F5D1": "Clear prompt"
     "\u{1f4cb}": "Apply selected styles to current prompt",
 
     "Inpaint a part of image": "Draw a mask over an image, and the script will regenerate the masked area with content according to prompt",
diff --git a/javascript/ui.js b/javascript/ui.js
index 2ca66d79..2cb280e5 100644
--- a/javascript/ui.js
+++ b/javascript/ui.js
@@ -131,6 +131,15 @@ function ask_for_style_name(_, prompt_text, negative_prompt_text) {
     return [name_, prompt_text, negative_prompt_text]
 }
 
+function confirm_clear_prompt(prompt, negative_prompt) {
+    if(confirm("Delete prompt?")) {
+        prompt = ""
+        negative_prompt = ""
+    }
+
+    return [prompt, negative_prompt]
+}
+
 
 
 opts = {}
diff --git a/launch.py b/launch.py
index 0e1bbaf2..af0d418b 100644
--- a/launch.py
+++ b/launch.py
@@ -157,7 +157,7 @@ def run_extensions_installers(settings_file):
         run_extension_installer(os.path.join(dir_extensions, dirname_extension))

 

 

-def prepare_enviroment():

+def prepare_environment():

     torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113")

     requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")

     commandline_args = os.environ.get('COMMANDLINE_ARGS', "")

@@ -291,5 +291,5 @@ def start():
 

 

 if __name__ == "__main__":

-    prepare_enviroment()

+    prepare_environment()

     start()

diff --git a/modules/api/api.py b/modules/api/api.py
index 54ee7cb0..89935a70 100644
--- a/modules/api/api.py
+++ b/modules/api/api.py
@@ -157,12 +157,7 @@ class Api:
         args.pop('include_init_images', None)  # this is meant to be done by "exclude": True in model, but it's for a reason that I cannot determine.
         p = StableDiffusionProcessingImg2Img(**args)
 
-        imgs = []
-        for img in init_images:
-            img = decode_base64_to_image(img)
-            imgs = [img] * p.batch_size
-
-        p.init_images = imgs
+        p.init_images = [decode_base64_to_image(x) for x in init_images]
 
         shared.state.begin()
 
diff --git a/modules/extras.py b/modules/extras.py
index bc349d5e..0ad8deec 100644
--- a/modules/extras.py
+++ b/modules/extras.py
@@ -62,7 +62,7 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
     # Also keep track of original file names

     imageNameArr = []

     outputs = []

-    

+

     if extras_mode == 1:

         #convert file to pillow image

         for img in image_folder:

@@ -234,7 +234,7 @@ def run_pnginfo(image):
     return '', geninfo, info

 

 

-def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format):

+def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format):

     def weighted_sum(theta0, theta1, alpha):

         return ((1 - alpha) * theta0) + (alpha * theta1)

 

@@ -246,30 +246,25 @@ def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_nam
 

     primary_model_info = sd_models.checkpoints_list[primary_model_name]

     secondary_model_info = sd_models.checkpoints_list[secondary_model_name]

-    teritary_model_info = sd_models.checkpoints_list.get(teritary_model_name, None)

+    tertiary_model_info = sd_models.checkpoints_list.get(tertiary_model_name, None)

     result_is_inpainting_model = False

 

-    print(f"Loading {primary_model_info.filename}...")

-    theta_0 = sd_models.read_state_dict(primary_model_info.filename, map_location='cpu')

-

-    print(f"Loading {secondary_model_info.filename}...")

-    theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu')

-

-    if teritary_model_info is not None:

-        print(f"Loading {teritary_model_info.filename}...")

-        theta_2 = sd_models.read_state_dict(teritary_model_info.filename, map_location='cpu')

-    else:

-        theta_2 = None

-

     theta_funcs = {

         "Weighted sum": (None, weighted_sum),

         "Add difference": (get_difference, add_difference),

     }

     theta_func1, theta_func2 = theta_funcs[interp_method]

 

-    print(f"Merging...")

+    if theta_func1 and not tertiary_model_info:

+        return ["Failed: Interpolation method requires a tertiary model."] + [gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)]

+

+    print(f"Loading {secondary_model_info.filename}...")

+    theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu')

 

     if theta_func1:

+        print(f"Loading {tertiary_model_info.filename}...")

+        theta_2 = sd_models.read_state_dict(tertiary_model_info.filename, map_location='cpu')

+

         for key in tqdm.tqdm(theta_1.keys()):

             if 'model' in key:

                 if key in theta_2:

@@ -277,7 +272,12 @@ def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_nam
                     theta_1[key] = theta_func1(theta_1[key], t2)

                 else:

                     theta_1[key] = torch.zeros_like(theta_1[key])

-    del theta_2

+        del theta_2

+

+    print(f"Loading {primary_model_info.filename}...")

+    theta_0 = sd_models.read_state_dict(primary_model_info.filename, map_location='cpu')

+

+    print("Merging...")

 

     for key in tqdm.tqdm(theta_0.keys()):

         if 'model' in key and key in theta_1:

@@ -307,6 +307,7 @@ def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_nam
             theta_0[key] = theta_1[key]

             if save_as_half:

                 theta_0[key] = theta_0[key].half()

+    del theta_1

 

     ckpt_dir = shared.cmd_opts.ckpt_dir or sd_models.model_path

 

@@ -332,5 +333,5 @@ def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_nam
 

     sd_models.list_models()

 

-    print(f"Checkpoint saved.")

+    print("Checkpoint saved.")

     return ["Checkpoint saved to " + output_modelname] + [gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)]

diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py
index 44fe1a6c..565e342d 100644
--- a/modules/generation_parameters_copypaste.py
+++ b/modules/generation_parameters_copypaste.py
@@ -77,6 +77,7 @@ def integrate_settings_paste_fields(component_dict):
         'inpainting_mask_weight': 'Conditional mask weight',

         'sd_model_checkpoint': 'Model hash',

         'eta_noise_seed_delta': 'ENSD',

+        'initial_noise_multiplier': 'Noise multiplier',

     }

     settings_paste_fields = [

         (component_dict[k], lambda d, k=k, v=v: ui.apply_setting(k, d.get(v, None)))

@@ -121,8 +122,7 @@ def run_bind():
 

             if send_generate_info and paste_fields[tab]["fields"] is not None:

                 if send_generate_info in paste_fields:

-                    paste_field_names = ['Prompt', 'Negative prompt', 'Steps', 'Face restoration', 'Size-1', 'Size-2'] + (["Seed"] if shared.opts.send_seed else [])

-

+                    paste_field_names = ['Prompt', 'Negative prompt', 'Steps', 'Face restoration'] +  (['Size-1', 'Size-2'] if shared.opts.send_size else []) + (["Seed"] if shared.opts.send_seed else [])

                     button.click(

                         fn=lambda *x: x,

                         inputs=[field for field, name in paste_fields[send_generate_info]["fields"] if name in paste_field_names],

diff --git a/modules/images.py b/modules/images.py
index 08a72e67..8146f580 100644
--- a/modules/images.py
+++ b/modules/images.py
@@ -501,30 +501,39 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     image = params.image

     fullfn = params.filename

     info = params.pnginfo.get(pnginfo_section_name, None)

-    fullfn_without_extension, extension = os.path.splitext(params.filename)

 

-    def exif_bytes():

-        return piexif.dump({

-            "Exif": {

-                piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(info or "", encoding="unicode")

-            },

-        })

+    def _atomically_save_image(image_to_save, filename_without_extension, extension):

+        # save image with .tmp extension to avoid race condition when another process detects new image in the directory

+        temp_file_path = filename_without_extension + ".tmp"

+        image_format = Image.registered_extensions()[extension]

 

-    if extension.lower() == '.png':

-        pnginfo_data = PngImagePlugin.PngInfo()

-        if opts.enable_pnginfo:

-            for k, v in params.pnginfo.items():

-                pnginfo_data.add_text(k, str(v))

+        if extension.lower() == '.png':

+            pnginfo_data = PngImagePlugin.PngInfo()

+            if opts.enable_pnginfo:

+                for k, v in params.pnginfo.items():

+                    pnginfo_data.add_text(k, str(v))

 

-        image.save(fullfn, quality=opts.jpeg_quality, pnginfo=pnginfo_data)

+            image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality, pnginfo=pnginfo_data)

 

-    elif extension.lower() in (".jpg", ".jpeg", ".webp"):

-        image.save(fullfn, quality=opts.jpeg_quality)

+        elif extension.lower() in (".jpg", ".jpeg", ".webp"):

+            image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality)

 

-        if opts.enable_pnginfo and info is not None:

-            piexif.insert(exif_bytes(), fullfn)

-    else:

-        image.save(fullfn, quality=opts.jpeg_quality)

+            if opts.enable_pnginfo and info is not None:

+                exif_bytes = piexif.dump({

+                    "Exif": {

+                        piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(info or "", encoding="unicode")

+                    },

+                })

+

+                piexif.insert(exif_bytes, temp_file_path)

+        else:

+            image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality)

+

+        # atomically rename the file with correct extension

+        os.replace(temp_file_path, filename_without_extension + extension)

+

+    fullfn_without_extension, extension = os.path.splitext(params.filename)

+    _atomically_save_image(image, fullfn_without_extension, extension)

 

     image.already_saved_as = fullfn

 

@@ -538,9 +547,7 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
         elif oversize:

             image = image.resize((image.width * target_side_length // image.height, target_side_length), LANCZOS)

 

-        image.save(fullfn_without_extension + ".jpg", quality=opts.jpeg_quality)

-        if opts.enable_pnginfo and info is not None:

-            piexif.insert(exif_bytes(), fullfn_without_extension + ".jpg")

+        _atomically_save_image(image, fullfn_without_extension, ".jpg")

 

     if opts.save_txt and info is not None:

         txt_fullfn = f"{fullfn_without_extension}.txt"

diff --git a/modules/processing.py b/modules/processing.py
index 3d2c4dc9..24c537d1 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -13,15 +13,20 @@ from skimage import exposure
 from typing import Any, Dict, List, Optional

 

 import modules.sd_hijack

-from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste

+from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, script_callbacks

 from modules.sd_hijack import model_hijack

 from modules.shared import opts, cmd_opts, state

 import modules.shared as shared

 import modules.face_restoration

 import modules.images as images

 import modules.styles

+import modules.sd_models as sd_models

+import modules.sd_vae as sd_vae

 import logging

+from ldm.data.util import AddMiDaS

+from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion

 

+from einops import repeat, rearrange

 

 # some of those options should not be changed at all because they would break the model, so I removed them from options.

 opt_C = 4

@@ -150,11 +155,26 @@ class StableDiffusionProcessing():
 

         return image_conditioning

 

-    def img2img_image_conditioning(self, source_image, latent_image, image_mask = None):

-        if self.sampler.conditioning_key not in {'hybrid', 'concat'}:

-            # Dummy zero conditioning if we're not using inpainting model.

-            return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)

+    def depth2img_image_conditioning(self, source_image):

+        # Use the AddMiDaS helper to Format our source image to suit the MiDaS model

+        transformer = AddMiDaS(model_type="dpt_hybrid")

+        transformed = transformer({"jpg": rearrange(source_image[0], "c h w -> h w c")})

+        midas_in = torch.from_numpy(transformed["midas_in"][None, ...]).to(device=shared.device)

+        midas_in = repeat(midas_in, "1 ... -> n ...", n=self.batch_size)

+

+        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))

+        conditioning = torch.nn.functional.interpolate(

+            self.sd_model.depth_model(midas_in),

+            size=conditioning_image.shape[2:],

+            mode="bicubic",

+            align_corners=False,

+        )

 

+        (depth_min, depth_max) = torch.aminmax(conditioning)

+        conditioning = 2. * (conditioning - depth_min) / (depth_max - depth_min) - 1.

+        return conditioning

+

+    def inpainting_image_conditioning(self, source_image, latent_image, image_mask = None):

         self.is_using_inpainting_conditioning = True

 

         # Handle the different mask inputs

@@ -191,6 +211,18 @@ class StableDiffusionProcessing():
 

         return image_conditioning

 

+    def img2img_image_conditioning(self, source_image, latent_image, image_mask=None):

+        # HACK: Using introspection as the Depth2Image model doesn't appear to uniquely

+        # identify itself with a field common to all models. The conditioning_key is also hybrid.

+        if isinstance(self.sd_model, LatentDepth2ImageDiffusion):

+            return self.depth2img_image_conditioning(source_image)

+

+        if self.sampler.conditioning_key in {'hybrid', 'concat'}:

+            return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)

+

+        # Dummy zero conditioning if we're not using inpainting or depth model.

+        return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)

+

     def init(self, all_prompts, all_seeds, all_subseeds):

         pass

 

@@ -424,8 +456,10 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
 

     try:

         for k, v in p.override_settings.items():

-            setattr(opts, k, v)  # we don't call onchange for simplicity which makes changing model impossible

-            if k == 'sd_hypernetwork': shared.reload_hypernetworks()  # make onchange call for changing hypernet since it is relatively fast to load on-change, while SD models are not

+            setattr(opts, k, v)

+            if k == 'sd_hypernetwork': shared.reload_hypernetworks()  # make onchange call for changing hypernet

+            if k == 'sd_model_checkpoint': sd_models.reload_model_weights()  # make onchange call for changing SD model

+            if k == 'sd_vae': sd_vae.reload_vae_weights()  # make onchange call for changing VAE

 

         res = process_images_inner(p)

 

@@ -433,6 +467,8 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
         for k, v in stored_opts.items():

             setattr(opts, k, v)

             if k == 'sd_hypernetwork': shared.reload_hypernetworks()

+            if k == 'sd_model_checkpoint': sd_models.reload_model_weights()

+            if k == 'sd_vae': sd_vae.reload_vae_weights()

 

     return res

 

@@ -541,9 +577,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 

             devices.torch_gc()

 

-            if opts.filter_nsfw:

-                import modules.safety as safety

-                x_samples_ddim = modules.safety.censor_batch(x_samples_ddim)

+            if p.scripts is not None:

+                p.scripts.postprocess_batch(p, x_samples_ddim, batch_number=n)

 

             for i, x_sample in enumerate(x_samples_ddim):

                 x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)

@@ -734,7 +769,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):

     sampler = None

 

-    def __init__(self, init_images: list=None, resize_mode: int=0, denoising_strength: float=0.75, mask: Any=None, mask_blur: int=4, inpainting_fill: int=0, inpaint_full_res: bool=True, inpaint_full_res_padding: int=0, inpainting_mask_invert: int=0, **kwargs):

+    def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.75, mask: Any = None, mask_blur: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, **kwargs):

         super().__init__(**kwargs)

 

         self.init_images = init_images

@@ -749,6 +784,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
         self.inpaint_full_res = inpaint_full_res

         self.inpaint_full_res_padding = inpaint_full_res_padding

         self.inpainting_mask_invert = inpainting_mask_invert

+        self.initial_noise_multiplier = opts.initial_noise_multiplier if initial_noise_multiplier is None else initial_noise_multiplier

         self.mask = None

         self.nmask = None

         self.image_conditioning = None

@@ -862,6 +898,10 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
     def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):

         x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)

 

+        if self.initial_noise_multiplier != 1.0:

+            self.extra_generation_params["Noise multiplier"] = self.initial_noise_multiplier

+            x *= self.initial_noise_multiplier

+

         samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)

 

         if self.mask is not None:

diff --git a/modules/safety.py b/modules/safety.py
deleted file mode 100644
index cff4b278..00000000
--- a/modules/safety.py
+++ /dev/null
@@ -1,42 +0,0 @@
-import torch

-from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker

-from transformers import AutoFeatureExtractor

-from PIL import Image

-

-import modules.shared as shared

-

-safety_model_id = "CompVis/stable-diffusion-safety-checker"

-safety_feature_extractor = None

-safety_checker = None

-

-def numpy_to_pil(images):

-    """

-    Convert a numpy image or a batch of images to a PIL image.

-    """

-    if images.ndim == 3:

-        images = images[None, ...]

-    images = (images * 255).round().astype("uint8")

-    pil_images = [Image.fromarray(image) for image in images]

-

-    return pil_images

-

-# check and replace nsfw content

-def check_safety(x_image):

-    global safety_feature_extractor, safety_checker

-

-    if safety_feature_extractor is None:

-        safety_feature_extractor = AutoFeatureExtractor.from_pretrained(safety_model_id)

-        safety_checker = StableDiffusionSafetyChecker.from_pretrained(safety_model_id)

-

-    safety_checker_input = safety_feature_extractor(numpy_to_pil(x_image), return_tensors="pt")

-    x_checked_image, has_nsfw_concept = safety_checker(images=x_image, clip_input=safety_checker_input.pixel_values)

-

-    return x_checked_image, has_nsfw_concept

-

-

-def censor_batch(x):

-    x_samples_ddim_numpy = x.cpu().permute(0, 2, 3, 1).numpy()

-    x_checked_image, has_nsfw_concept = check_safety(x_samples_ddim_numpy)

-    x = torch.from_numpy(x_checked_image).permute(0, 3, 1, 2)

-

-    return x

diff --git a/modules/scripts.py b/modules/scripts.py
index b934d881..23ca195d 100644
--- a/modules/scripts.py
+++ b/modules/scripts.py
@@ -88,6 +88,17 @@ class Script:
 

         pass

 

+    def postprocess_batch(self, p, *args, **kwargs):

+        """

+        Same as process_batch(), but called for every batch after it has been generated.

+

+        **kwargs will have same items as process_batch, and also:

+          - batch_number - index of current batch, from 0 to number of batches-1

+          - images - torch tensor with all generated images, with values ranging from 0 to 1;

+        """

+

+        pass

+

     def postprocess(self, p, processed, *args):

         """

         This function is called after processing ends for AlwaysVisible scripts.

@@ -347,6 +358,15 @@ class ScriptRunner:
                 print(f"Error running postprocess: {script.filename}", file=sys.stderr)

                 print(traceback.format_exc(), file=sys.stderr)

 

+    def postprocess_batch(self, p, images, **kwargs):

+        for script in self.alwayson_scripts:

+            try:

+                script_args = p.script_args[script.args_from:script.args_to]

+                script.postprocess_batch(p, *script_args, images=images, **kwargs)

+            except Exception:

+                print(f"Error running postprocess_batch: {script.filename}", file=sys.stderr)

+                print(traceback.format_exc(), file=sys.stderr)

+

     def before_component(self, component, **kwargs):

         for script in self.scripts:

             try:

diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py
index 95a17093..690a9ec2 100644
--- a/modules/sd_hijack.py
+++ b/modules/sd_hijack.py
@@ -1,17 +1,11 @@
-import math

-import os

-import sys

-import traceback

 import torch

-import numpy as np

-from torch import einsum

 from torch.nn.functional import silu

 

 import modules.textual_inversion.textual_inversion

-from modules import prompt_parser, devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint

+from modules import devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint

 from modules.hypernetworks import hypernetwork

-from modules.shared import opts, device, cmd_opts

-from modules import sd_hijack_clip, sd_hijack_open_clip

+from modules.shared import cmd_opts

+from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet

 

 from modules.sd_hijack_optimizations import invokeAI_mps_available

 

@@ -35,10 +29,12 @@ ldm.modules.attention.BasicTransformerBlock.ATTENTION_MODES["softmax-xformers"]
 ldm.modules.attention.print = lambda *args: None

 ldm.modules.diffusionmodules.model.print = lambda *args: None

 

+

 def apply_optimizations():

     undo_optimizations()

 

     ldm.modules.diffusionmodules.model.nonlinearity = silu

+    ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th

 

     if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)):

         print("Applying xformers cross attention optimization.")

diff --git a/modules/sd_hijack_unet.py b/modules/sd_hijack_unet.py
new file mode 100644
index 00000000..1b9d7757
--- /dev/null
+++ b/modules/sd_hijack_unet.py
@@ -0,0 +1,30 @@
+import torch

+

+

+class TorchHijackForUnet:

+    """

+    This is torch, but with cat that resizes tensors to appropriate dimensions if they do not match;

+    this makes it possible to create pictures with dimensions that are muliples of 8 rather than 64

+    """

+

+    def __getattr__(self, item):

+        if item == 'cat':

+            return self.cat

+

+        if hasattr(torch, item):

+            return getattr(torch, item)

+

+        raise AttributeError("'{}' object has no attribute '{}'".format(type(self).__name__, item))

+

+    def cat(self, tensors, *args, **kwargs):

+        if len(tensors) == 2:

+            a, b = tensors

+            if a.shape[-2:] != b.shape[-2:]:

+                a = torch.nn.functional.interpolate(a, b.shape[-2:], mode="nearest")

+

+            tensors = (a, b)

+

+        return torch.cat(tensors, *args, **kwargs)

+

+

+th = TorchHijackForUnet()

diff --git a/modules/sd_models.py b/modules/sd_models.py
index 283cf1cd..5b37f3fe 100644
--- a/modules/sd_models.py
+++ b/modules/sd_models.py
@@ -7,6 +7,9 @@ import torch
 import re

 import safetensors.torch

 from omegaconf import OmegaConf

+from os import mkdir

+from urllib import request

+import ldm.modules.midas as midas

 

 from ldm.util import instantiate_from_config

 

@@ -36,6 +39,7 @@ def setup_model():
         os.makedirs(model_path)

 

     list_models()

+    enable_midas_autodownload()

 

 

 def checkpoint_tiles(): 

@@ -223,10 +227,54 @@ def load_model_weights(model, checkpoint_info, vae_file="auto"):
     model.sd_model_checkpoint = checkpoint_file

     model.sd_checkpoint_info = checkpoint_info

 

+    sd_vae.delete_base_vae()

+    sd_vae.clear_loaded_vae()

     vae_file = sd_vae.resolve_vae(checkpoint_file, vae_file=vae_file)

     sd_vae.load_vae(model, vae_file)

 

 

+def enable_midas_autodownload():

+    """

+    Gives the ldm.modules.midas.api.load_model function automatic downloading.

+

+    When the 512-depth-ema model, and other future models like it, is loaded,

+    it calls midas.api.load_model to load the associated midas depth model.

+    This function applies a wrapper to download the model to the correct

+    location automatically.

+    """

+

+    midas_path = os.path.join(models_path, 'midas')

+

+    # stable-diffusion-stability-ai hard-codes the midas model path to

+    # a location that differs from where other scripts using this model look.

+    # HACK: Overriding the path here.

+    for k, v in midas.api.ISL_PATHS.items():

+        file_name = os.path.basename(v)

+        midas.api.ISL_PATHS[k] = os.path.join(midas_path, file_name)

+

+    midas_urls = {

+        "dpt_large": "https://github.com/intel-isl/DPT/releases/download/1_0/dpt_large-midas-2f21e586.pt",

+        "dpt_hybrid": "https://github.com/intel-isl/DPT/releases/download/1_0/dpt_hybrid-midas-501f0c75.pt",

+        "midas_v21": "https://github.com/AlexeyAB/MiDaS/releases/download/midas_dpt/midas_v21-f6b98070.pt",

+        "midas_v21_small": "https://github.com/AlexeyAB/MiDaS/releases/download/midas_dpt/midas_v21_small-70d6b9c8.pt",

+    }

+

+    midas.api.load_model_inner = midas.api.load_model

+

+    def load_model_wrapper(model_type):

+        path = midas.api.ISL_PATHS[model_type]

+        if not os.path.exists(path):

+            if not os.path.exists(midas_path):

+                mkdir(midas_path)

+    

+            print(f"Downloading midas model weights for {model_type} to {path}")

+            request.urlretrieve(midas_urls[model_type], path)

+            print(f"{model_type} downloaded")

+

+        return midas.api.load_model_inner(model_type)

+

+    midas.api.load_model = load_model_wrapper

+

 def load_model(checkpoint_info=None):

     from modules import lowvram, sd_hijack

     checkpoint_info = checkpoint_info or select_checkpoint()

diff --git a/modules/sd_vae.py b/modules/sd_vae.py
index 9c120975..25638a83 100644
--- a/modules/sd_vae.py
+++ b/modules/sd_vae.py
@@ -4,6 +4,7 @@ from collections import namedtuple
 from modules import shared, devices, script_callbacks
 from modules.paths import models_path
 import glob
+from copy import deepcopy
 
 
 model_dir = "Stable-diffusion"
@@ -15,7 +16,7 @@ vae_path = os.path.abspath(os.path.join(models_path, vae_dir))
 vae_ignore_keys = {"model_ema.decay", "model_ema.num_updates"}
 
 
-default_vae_dict = {"auto": "auto", "None": "None"}
+default_vae_dict = {"auto": "auto", "None": None, None: None}
 default_vae_list = ["auto", "None"]
 
 
@@ -39,7 +40,8 @@ def get_base_vae(model):
 def store_base_vae(model):
     global base_vae, checkpoint_info
     if checkpoint_info != model.sd_checkpoint_info:
-        base_vae = model.first_stage_model.state_dict().copy()
+        assert not loaded_vae_file, "Trying to store non-base VAE!"
+        base_vae = deepcopy(model.first_stage_model.state_dict())
         checkpoint_info = model.sd_checkpoint_info
 
 
@@ -50,9 +52,11 @@ def delete_base_vae():
 
 
 def restore_base_vae(model):
-    global base_vae, checkpoint_info
+    global loaded_vae_file
     if base_vae is not None and checkpoint_info == model.sd_checkpoint_info:
-        load_vae_dict(model, base_vae)
+        print("Restoring base VAE")
+        _load_vae_dict(model, base_vae)
+        loaded_vae_file = None
     delete_base_vae()
 
 
@@ -148,9 +152,10 @@ def load_vae(model, vae_file=None):
     if vae_file:
         assert os.path.isfile(vae_file), f"VAE file doesn't exist: {vae_file}"
         print(f"Loading VAE weights from: {vae_file}")
+        store_base_vae(model)
         vae_ckpt = torch.load(vae_file, map_location=shared.weight_load_location)
         vae_dict_1 = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss" and k not in vae_ignore_keys}
-        load_vae_dict(model, vae_dict_1)
+        _load_vae_dict(model, vae_dict_1)
 
         # If vae used is not in dict, update it
         # It will be removed on refresh though
@@ -158,30 +163,22 @@ def load_vae(model, vae_file=None):
         if vae_opt not in vae_dict:
             vae_dict[vae_opt] = vae_file
             vae_list.append(vae_opt)
+    elif loaded_vae_file:
+        restore_base_vae(model)
 
     loaded_vae_file = vae_file
 
-    """
-    # Save current VAE to VAE settings, maybe? will it work?
-    if save_settings:
-        if vae_file is None:
-            vae_opt = "None"
-
-        # shared.opts.sd_vae = vae_opt
-    """
-
     first_load = False
 
 
 # don't call this from outside
-def load_vae_dict(model, vae_dict_1=None):
-    if vae_dict_1:
-        store_base_vae(model)
-        model.first_stage_model.load_state_dict(vae_dict_1)
-    else:
-        restore_base_vae()
+def _load_vae_dict(model, vae_dict_1):
+    model.first_stage_model.load_state_dict(vae_dict_1)
     model.first_stage_model.to(devices.dtype_vae)
 
+def clear_loaded_vae():
+    global loaded_vae_file
+    loaded_vae_file = None
 
 def reload_vae_weights(sd_model=None, vae_file="auto"):
     from modules import lowvram, devices, sd_hijack
diff --git a/modules/shared.py b/modules/shared.py
index dc45fcaa..272267c1 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -359,6 +359,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "sd_hypernetwork": OptionInfo("None", "Hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks),

     "sd_hypernetwork_strength": OptionInfo(1.0, "Hypernetwork strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.001}),

     "inpainting_mask_weight": OptionInfo(1.0, "Inpainting conditioning mask strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),

+    "initial_noise_multiplier": OptionInfo(1.0, "Noise multiplier for img2img", gr.Slider, {"minimum": 0.5, "maximum": 1.5, "step": 0.01 }),

     "img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."),

     "img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising)."),

     "enable_quantization": OptionInfo(False, "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply."),

@@ -366,7 +367,6 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),

     "enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"),

     "comma_padding_backtrack": OptionInfo(20, "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1 }),

-    "filter_nsfw": OptionInfo(False, "Filter NSFW content"),

     'CLIP_stop_at_last_layers': OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}),

     "random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}),

 }))

@@ -395,6 +395,7 @@ options_templates.update(options_section(('ui', "User interface"), {
     "add_model_name_to_info": OptionInfo(False, "Add model name to generation information"),

     "disable_weights_auto_swap": OptionInfo(False, "When reading generation parameters from text into UI (from PNG info or pasted text), do not change the selected model/checkpoint."),

     "send_seed": OptionInfo(True, "Send seed when sending prompt or image to other interface"),

+    "send_size": OptionInfo(True, "Send size when sending prompt or image to another interface"),

     "font": OptionInfo("", "Font for image grids that have text"),

     "js_modal_lightbox": OptionInfo(True, "Enable full page image viewer"),

     "js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),

diff --git a/modules/ui.py b/modules/ui.py
index b2b8de90..28481e33 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -82,6 +82,7 @@ folder_symbol = '\U0001f4c2'  # 📂
 refresh_symbol = '\U0001f504'  # 🔄

 save_style_symbol = '\U0001f4be'  # 💾

 apply_style_symbol = '\U0001f4cb'  # 📋

+clear_prompt_symbol = '\U0001F5D1'  # 🗑️

 

 

 def plaintext_to_html(text):

@@ -302,8 +303,8 @@ def create_seed_inputs():
 

     with gr.Row(visible=False) as seed_extra_row_2:

         seed_extras.append(seed_extra_row_2)

-        seed_resize_from_w = gr.Slider(minimum=0, maximum=2048, step=64, label="Resize seed from width", value=0)

-        seed_resize_from_h = gr.Slider(minimum=0, maximum=2048, step=64, label="Resize seed from height", value=0)

+        seed_resize_from_w = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from width", value=0)

+        seed_resize_from_h = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from height", value=0)

 

     random_seed.click(fn=lambda: -1, show_progress=False, inputs=[], outputs=[seed])

     random_subseed.click(fn=lambda: -1, show_progress=False, inputs=[], outputs=[subseed])

@@ -316,6 +317,17 @@ def create_seed_inputs():
     return seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox

 

 

+

+def connect_clear_prompt(button):

+    """Given clear button, prompt, and token_counter objects, setup clear prompt button click event"""

+    button.click(

+        _js="clear_prompt",

+        fn=None,

+        inputs=[],

+        outputs=[],

+    )

+

+

 def connect_reuse_seed(seed: gr.Number, reuse_seed: gr.Button, generation_info: gr.Textbox, dummy_component, is_subseed):

     """ Connects a 'reuse (sub)seed' button's click event so that it copies last used

         (sub)seed value from generation info the to the seed field. If copying subseed and subseed strength

@@ -391,10 +403,17 @@ def create_toprow(is_img2img):
             paste = gr.Button(value=paste_symbol, elem_id="paste")

             save_style = gr.Button(value=save_style_symbol, elem_id="style_create")

             prompt_style_apply = gr.Button(value=apply_style_symbol, elem_id="style_apply")

-

+            clear_prompt_button = gr.Button(value=clear_prompt_symbol, elem_id=f"{id_part}_clear_prompt")

             token_counter = gr.HTML(value="<span></span>", elem_id=f"{id_part}_token_counter")

             token_button = gr.Button(visible=False, elem_id=f"{id_part}_token_button")

 

+            clear_prompt_button.click(

+                fn=lambda *x: x,

+                _js="confirm_clear_prompt",

+                inputs=[prompt, negative_prompt],

+                outputs=[prompt, negative_prompt],

+            )

+

         button_interrogate = None

         button_deepbooru = None

         if is_img2img:

@@ -616,10 +635,14 @@ def create_ui():
     modules.scripts.scripts_txt2img.initialize_scripts(is_img2img=False)

 

     with gr.Blocks(analytics_enabled=False) as txt2img_interface:

-        txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, _, txt2img_prompt_style_apply, txt2img_save_style, txt2img_paste, token_counter, token_button = create_toprow(is_img2img=False)

+        txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, _,txt2img_prompt_style_apply, txt2img_save_style, txt2img_paste, token_counter, token_button = create_toprow(is_img2img=False)

+

         dummy_component = gr.Label(visible=False)

         txt_prompt_img = gr.File(label="", elem_id="txt2img_prompt_image", file_count="single", type="bytes", visible=False)

 

+

+

+

         with gr.Row(elem_id='txt2img_progress_row'):

             with gr.Column(scale=1):

                 pass

@@ -635,8 +658,8 @@ def create_ui():
                 sampler_index = gr.Radio(label='Sampling method', elem_id="txt2img_sampling", choices=[x.name for x in samplers], value=samplers[0].name, type="index")

 

                 with gr.Group():

-                    width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)

-                    height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)

+                    width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)

+                    height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)

 

                 with gr.Row():

                     restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1)

@@ -644,8 +667,8 @@ def create_ui():
                     enable_hr = gr.Checkbox(label='Highres. fix', value=False)

 

                 with gr.Row(visible=False) as hr_options:

-                    firstphase_width = gr.Slider(minimum=0, maximum=1024, step=64, label="Firstpass width", value=0)

-                    firstphase_height = gr.Slider(minimum=0, maximum=1024, step=64, label="Firstpass height", value=0)

+                    firstphase_width = gr.Slider(minimum=0, maximum=1024, step=8, label="Firstpass width", value=0)

+                    firstphase_height = gr.Slider(minimum=0, maximum=1024, step=8, label="Firstpass height", value=0)

                     denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7)

 

                 with gr.Row(equal_height=True):

@@ -770,7 +793,8 @@ def create_ui():
     modules.scripts.scripts_img2img.initialize_scripts(is_img2img=True)

 

     with gr.Blocks(analytics_enabled=False) as img2img_interface:

-        img2img_prompt, roll, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_deepbooru, img2img_prompt_style_apply, img2img_save_style, img2img_paste, token_counter, token_button = create_toprow(is_img2img=True)

+        img2img_prompt, roll, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_deepbooru, img2img_prompt_style_apply, img2img_save_style, img2img_paste,token_counter, token_button = create_toprow(is_img2img=True)

+

 

         with gr.Row(elem_id='img2img_progress_row'):

             img2img_prompt_img = gr.File(label="", elem_id="img2img_prompt_image", file_count="single", type="bytes", visible=False)

@@ -835,8 +859,8 @@ def create_ui():
                 sampler_index = gr.Radio(label='Sampling method', choices=[x.name for x in samplers_for_img2img], value=samplers_for_img2img[0].name, type="index")

 

                 with gr.Group():

-                    width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512, elem_id="img2img_width")

-                    height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512, elem_id="img2img_height")

+                    width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")

+                    height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height")

 

                 with gr.Row():

                     restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1)

@@ -1171,8 +1195,8 @@ def create_ui():
                 with gr.Tab(label="Preprocess images"):

                     process_src = gr.Textbox(label='Source directory')

                     process_dst = gr.Textbox(label='Destination directory')

-                    process_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)

-                    process_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)

+                    process_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)

+                    process_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)

                     preprocess_txt_action = gr.Dropdown(label='Existing Caption txt Action', value="ignore", choices=["ignore", "copy", "prepend", "append"])

 

                     with gr.Row():

@@ -1230,8 +1254,8 @@ def create_ui():
                     dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")

                     log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion")

                     template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt"))

-                    training_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)

-                    training_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)

+                    training_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)

+                    training_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)

                     steps = gr.Number(label='Max steps', value=100000, precision=0)

                     create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0)

                     save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0)

@@ -1450,7 +1474,7 @@ def create_ui():
             opts.save(shared.config_filename)

         except RuntimeError:

             return opts.dumpjson(), f'{len(changed)} settings changed without save: {", ".join(changed)}.'

-        return opts.dumpjson(), f'{len(changed)} settings changed: {", ".join(changed)}.'

+        return opts.dumpjson(), f'{len(changed)} settings changed{": " if len(changed) > 0 else ""}{", ".join(changed)}.'

 

     def run_settings_single(value, key):

         if not opts.same_type(value, opts.data_labels[key].default):

diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py
index b487ac25..1434f25f 100644
--- a/modules/ui_extensions.py
+++ b/modules/ui_extensions.py
@@ -206,12 +206,13 @@ def refresh_available_extensions_from_data(hide_tags):
         if url is None:

             continue

 

+        existing = installed_extension_urls.get(normalize_git_url(url), None)

+        extension_tags = extension_tags + ["installed"] if existing else extension_tags

+

         if len([x for x in extension_tags if x in tags_to_hide]) > 0:

             hidden += 1

             continue

 

-        existing = installed_extension_urls.get(normalize_git_url(url), None)

-

         install_code = f"""<input onclick="install_extension_from_index(this, '{html.escape(url)}')" type="button" value="{"Install" if not existing else "Installed"}" {"disabled=disabled" if existing else ""} class="gr-button gr-button-lg gr-button-secondary">"""

 

         tags_text = ", ".join([f"<span class='extension-tag' title='{tags.get(x, '')}'>{x}</span>" for x in extension_tags])

@@ -222,7 +223,11 @@ def refresh_available_extensions_from_data(hide_tags):
                 <td>{html.escape(description)}</td>

                 <td>{install_code}</td>

             </tr>

-    """

+        

+        """

+

+        for tag in [x for x in extension_tags if x not in tags]:

+            tags[tag] = tag

 

     code += """

         </tbody>

@@ -272,7 +277,7 @@ def create_ui():
                     install_extension_button = gr.Button(elem_id="install_extension_button", visible=False)

 

                 with gr.Row():

-                    hide_tags = gr.CheckboxGroup(value=["ads", "localization"], label="Hide extensions with tags", choices=["script", "ads", "localization"])

+                    hide_tags = gr.CheckboxGroup(value=["ads", "localization", "installed"], label="Hide extensions with tags", choices=["script", "ads", "localization", "installed"])

 

                 install_result = gr.HTML()

                 available_extensions_table = gr.HTML()

diff --git a/requirements.txt b/requirements.txt
index 5f3d9623..678acb4d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,6 +1,5 @@
 accelerate

 basicsr

-diffusers

 fairscale==0.4.4

 fonts

 font-roboto

@@ -30,3 +29,4 @@ inflection
 GitPython

 torchsde

 safetensors

+psutil; sys_platform == 'darwin'

diff --git a/requirements_versions.txt b/requirements_versions.txt
index 035fa82f..185cd066 100644
--- a/requirements_versions.txt
+++ b/requirements_versions.txt
@@ -1,5 +1,4 @@
 transformers==4.19.2

-diffusers==0.3.0

 accelerate==0.12.0

 basicsr==1.4.2

 gfpgan==1.3.8

diff --git a/scripts/prompt_matrix.py b/scripts/prompt_matrix.py
index 5fd952e9..c53ca28c 100644
--- a/scripts/prompt_matrix.py
+++ b/scripts/prompt_matrix.py
@@ -46,10 +46,11 @@ class Script(scripts.Script):
 

     def ui(self, is_img2img):

         put_at_start = gr.Checkbox(label='Put variable parts at start of prompt', value=False)

+        different_seeds = gr.Checkbox(label='Use different seed for each picture', value=False)

 

-        return [put_at_start]

+        return [put_at_start, different_seeds]

 

-    def run(self, p, put_at_start):

+    def run(self, p, put_at_start, different_seeds):

         modules.processing.fix_seed(p)

 

         original_prompt = p.prompt[0] if type(p.prompt) == list else p.prompt

@@ -73,7 +74,7 @@ class Script(scripts.Script):
         print(f"Prompt matrix will create {len(all_prompts)} images using a total of {p.n_iter} batches.")

 

         p.prompt = all_prompts

-        p.seed = [p.seed for _ in all_prompts]

+        p.seed = [p.seed + (i if different_seeds else 0) for i in range(len(all_prompts))]

         p.prompt_for_display = original_prompt

         processed = process_images(p)

 

diff --git a/scripts/sd_upscale.py b/scripts/sd_upscale.py
index 01074291..28bd96b3 100644
--- a/scripts/sd_upscale.py
+++ b/scripts/sd_upscale.py
@@ -17,13 +17,14 @@ class Script(scripts.Script):
         return is_img2img

 

     def ui(self, is_img2img):

-        info = gr.HTML("<p style=\"margin-bottom:0.75em\">Will upscale the image to twice the dimensions; use width and height sliders to set tile size</p>")

+        info = gr.HTML("<p style=\"margin-bottom:0.75em\">Will upscale the image by the selected scale factor; use width and height sliders to set tile size</p>")

         overlap = gr.Slider(minimum=0, maximum=256, step=16, label='Tile overlap', value=64)

+        scale_factor = gr.Slider(minimum=1, maximum=4, step=1, label='Scale Factor', value=2)

         upscaler_index = gr.Radio(label='Upscaler', choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name, type="index")

 

-        return [info, overlap, upscaler_index]

+        return [info, overlap, upscaler_index, scale_factor]

 

-    def run(self, p, _, overlap, upscaler_index):

+    def run(self, p, _, overlap, upscaler_index, scale_factor):

         processing.fix_seed(p)

         upscaler = shared.sd_upscalers[upscaler_index]

 

@@ -34,9 +35,9 @@ class Script(scripts.Script):
         seed = p.seed

 

         init_img = p.init_images[0]

-        

-        if(upscaler.name != "None"): 

-            img = upscaler.scaler.upscale(init_img, 2, upscaler.data_path)

+

+        if (upscaler.name != "None"):

+            img = upscaler.scaler.upscale(init_img, scale_factor, upscaler.data_path)

         else:

             img = init_img

 

@@ -69,7 +70,7 @@ class Script(scripts.Script):
             work_results = []

             for i in range(batch_count):

                 p.batch_size = batch_size

-                p.init_images = work[i*batch_size:(i+1)*batch_size]

+                p.init_images = work[i * batch_size:(i + 1) * batch_size]

 

                 state.job = f"Batch {i + 1 + n * batch_count} out of {state.job_count}"

                 processed = processing.process_images(p)

diff --git a/style.css b/style.css
index e2b71f25..3ad78006 100644
--- a/style.css
+++ b/style.css
@@ -114,7 +114,7 @@
     padding: 0.4em 0;

 }

 

-#roll, #paste, #style_create, #style_apply{

+#roll_col > button {

     min-width: 2em;

     min-height: 2em;

     max-width: 2em;

diff --git a/webui-macos-env.sh b/webui-macos-env.sh
index 68d1f754..95ca9c55 100644
--- a/webui-macos-env.sh
+++ b/webui-macos-env.sh
@@ -4,6 +4,12 @@
 # Please modify webui-user.sh to change these instead of this file #
 ####################################################################
 
+if [[ -x "$(command -v python3.10)" ]]
+then
+    python_cmd="python3.10"
+fi
+
+export install_dir="$HOME"
 export COMMANDLINE_ARGS="--skip-torch-cuda-test --no-half --use-cpu interrogate"
 export TORCH_COMMAND="pip install torch==1.12.1 torchvision==0.13.1"
 export K_DIFFUSION_REPO="https://github.com/brkirch/k-diffusion.git"
diff --git a/webui.py b/webui.py
index 78204d11..c2d0c6be 100644
--- a/webui.py
+++ b/webui.py
@@ -137,7 +137,7 @@ def webui():
 

         shared.demo = modules.ui.create_ui()

 

-        app, local_url, share_url = shared.demo.launch(

+        app, local_url, share_url = shared.demo.queue(default_enabled=False).launch(

             share=cmd_opts.share,

             server_name=server_name,

             server_port=cmd_opts.port,