Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into Base

19 files changed, 1011 insertions, 115 deletions

diff --git a/.gitignore b/.gitignore
index 1dffb108..4f830e61 100644
--- a/.gitignore
+++ b/.gitignore
@@ -16,3 +16,4 @@ __pycache__
 /webui-user.bat
 /webui-user.sh
 /interrogate
+/user.css
diff --git a/README.md b/README.md
index 84a78da5..d97ebc3f 100644
--- a/README.md
+++ b/README.md
@@ -51,7 +51,7 @@ Alternatively, use [Google Colab](https://colab.research.google.com/drive/1Iy-xW
 1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH"

 2. Install [git](https://git-scm.com/download/win).

 3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.

-4. Place `model.ckpt` in the base directory, alongside `webui.py`.

+4. Place `model.ckpt` in the `models` directory.

 5. _*(Optional)*_ Place `GFPGANv1.3.pth` in the base directory, alongside `webui.py`.

 6. Run `webui-user.bat` from Windows Explorer as normal, non-administrate, user.

 

@@ -81,6 +81,7 @@ The documentation was moved from this README over to the project's [wiki](https:
 - Ideas for optimizations - https://github.com/basujindal/stable-diffusion

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

 - Idea for SD upscale - https://github.com/jquesnelle/txt2imghd

+- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot

 - CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator

 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.

 - (You)

diff --git a/models/Put Stable Diffusion checkpoints here.txt b/models/Put Stable Diffusion checkpoints here.txt
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/models/Put Stable Diffusion checkpoints here.txt
diff --git a/modules/devices.py b/modules/devices.py
index e4430e1a..07bb2339 100644
--- a/modules/devices.py
+++ b/modules/devices.py
@@ -48,3 +48,13 @@ def randn(seed, shape):
     torch.manual_seed(seed)
     return torch.randn(shape, device=device)
 
+
+def randn_without_seed(shape):
+    # Pytorch currently doesn't handle setting randomness correctly when the metal backend is used.
+    if device.type == 'mps':
+        generator = torch.Generator(device=cpu)
+        noise = torch.randn(shape, generator=generator, device=cpu).to(device)
+        return noise
+
+    return torch.randn(shape, device=device)
+
diff --git a/modules/extras.py b/modules/extras.py
index ffae7d67..3d9d9f7a 100644
--- a/modules/extras.py
+++ b/modules/extras.py
@@ -36,6 +36,7 @@ def run_extras(image, image_folder, gfpgan_visibility, codeformer_visibility, co
 

     outpath = opts.outdir_samples or opts.outdir_extras_samples

 

+    outputs = []

     for image in imageArr:

         existing_pnginfo = image.info or {}

 

@@ -91,7 +92,9 @@ def run_extras(image, image_folder, gfpgan_visibility, codeformer_visibility, co
 

         images.save_image(image, path=outpath, basename="", seed=None, prompt=None, extension=opts.samples_format, info=info, short_filename=True, no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo)

 

-    return imageArr, plaintext_to_html(info), ''

+        outputs.append(image)

+

+    return outputs, plaintext_to_html(info), ''

 

 

 def run_pnginfo(image):

@@ -108,8 +111,9 @@ def run_pnginfo(image):
 

         items['exif comment'] = exif_comment

 

-        for field in ['jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif']:

-            del items[field]

+        for field in ['jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif',

+                      'loop', 'background', 'timestamp', 'duration']:

+            items.pop(field, None)

 

 

     info = ''

diff --git a/modules/images.py b/modules/images.py
index f37f5f08..e287d0df 100644
--- a/modules/images.py
+++ b/modules/images.py
@@ -274,7 +274,7 @@ def apply_filename_pattern(x, p, seed, prompt):
         x = x.replace("[height]", str(p.height))

         x = x.replace("[sampler]", sd_samplers.samplers[p.sampler_index].name)

 

-    x = x.replace("[model_hash]", shared.sd_model_hash)

+    x = x.replace("[model_hash]", shared.sd_model.sd_model_hash)

     x = x.replace("[date]", datetime.date.today().isoformat())

 

     if cmd_opts.hide_ui_dir_config:

@@ -353,13 +353,12 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
         })

 

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

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

+        image.save(fullfn, 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, pnginfo=pnginfo)

 

-    if extension.lower() == "webp":

-        piexif.insert(exif_bytes, fullfn)

-

     target_side_length = 4000

     oversize = image.width > target_side_length or image.height > target_side_length

     if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > 4 * 1024 * 1024):

@@ -370,7 +369,9 @@ 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, exif_bytes=exif_bytes())

+        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")

 

     if opts.save_txt and info is not None:

         with open(f"{fullfn_without_extension}.txt", "w", encoding="utf8") as file:

diff --git a/modules/memmon.py b/modules/memmon.py
new file mode 100644
index 00000000..f2cac841
--- /dev/null
+++ b/modules/memmon.py
@@ -0,0 +1,77 @@
+import threading
+import time
+from collections import defaultdict
+
+import torch
+
+
+class MemUsageMonitor(threading.Thread):
+    run_flag = None
+    device = None
+    disabled = False
+    opts = None
+    data = None
+
+    def __init__(self, name, device, opts):
+        threading.Thread.__init__(self)
+        self.name = name
+        self.device = device
+        self.opts = opts
+
+        self.daemon = True
+        self.run_flag = threading.Event()
+        self.data = defaultdict(int)
+
+    def run(self):
+        if self.disabled:
+            return
+
+        while True:
+            self.run_flag.wait()
+
+            torch.cuda.reset_peak_memory_stats()
+            self.data.clear()
+
+            if self.opts.memmon_poll_rate <= 0:
+                self.run_flag.clear()
+                continue
+
+            self.data["min_free"] = torch.cuda.mem_get_info()[0]
+
+            while self.run_flag.is_set():
+                free, total = torch.cuda.mem_get_info()  # calling with self.device errors, torch bug?
+                self.data["min_free"] = min(self.data["min_free"], free)
+
+                time.sleep(1 / self.opts.memmon_poll_rate)
+
+    def dump_debug(self):
+        print(self, 'recorded data:')
+        for k, v in self.read().items():
+            print(k, -(v // -(1024 ** 2)))
+
+        print(self, 'raw torch memory stats:')
+        tm = torch.cuda.memory_stats(self.device)
+        for k, v in tm.items():
+            if 'bytes' not in k:
+                continue
+            print('\t' if 'peak' in k else '', k, -(v // -(1024 ** 2)))
+
+        print(torch.cuda.memory_summary())
+
+    def monitor(self):
+        self.run_flag.set()
+
+    def read(self):
+        free, total = torch.cuda.mem_get_info()
+        self.data["total"] = total
+
+        torch_stats = torch.cuda.memory_stats(self.device)
+        self.data["active_peak"] = torch_stats["active_bytes.all.peak"]
+        self.data["reserved_peak"] = torch_stats["reserved_bytes.all.peak"]
+        self.data["system_peak"] = total - self.data["min_free"]
+
+        return self.data
+
+    def stop(self):
+        self.run_flag.clear()
+        return self.read()
diff --git a/modules/processing.py b/modules/processing.py
index 71a9c6f5..6a99d383 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -119,8 +119,18 @@ def slerp(val, low, high):
     return res

 

 

-def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, seed_resize_from_h=0, seed_resize_from_w=0):

+def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, seed_resize_from_h=0, seed_resize_from_w=0, p=None):

     xs = []

+

+    # if we have multiple seeds, this means we are working with batch size>1; this then

+    # enables the generation of additional tensors with noise that the sampler will use during its processing.

+    # Using those pre-genrated tensors instead of siimple torch.randn allows a batch with seeds [100, 101] to

+    # produce the same images as with two batches [100], [101].

+    if p is not None and p.sampler is not None and len(seeds) > 1 and opts.enable_batch_seeds:

+        sampler_noises = [[] for _ in range(p.sampler.number_of_needed_noises(p))]

+    else:

+        sampler_noises = None

+

     for i, seed in enumerate(seeds):

         noise_shape = shape if seed_resize_from_h <= 0 or seed_resize_from_w <= 0 else (shape[0], seed_resize_from_h//8, seed_resize_from_w//8)

 

@@ -155,9 +165,17 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
             x[:, ty:ty+h, tx:tx+w] = noise[:, dy:dy+h, dx:dx+w]

             noise = x

 

+        if sampler_noises is not None:

+            cnt = p.sampler.number_of_needed_noises(p)

 

+            for j in range(cnt):

+                sampler_noises[j].append(devices.randn_without_seed(tuple(noise_shape)))

 

         xs.append(noise)

+

+    if sampler_noises is not None:

+        p.sampler.sampler_noises = [torch.stack(n).to(shared.device) for n in sampler_noises]

+

     x = torch.stack(xs).to(shared.device)

     return x

 

@@ -170,7 +188,11 @@ def fix_seed(p):
 def process_images(p: StableDiffusionProcessing) -> Processed:

     """this is the main loop that both txt2img and img2img use; it calls func_init once inside all the scopes and func_sample once per batch"""

 

-    assert p.prompt is not None

+    if type(p.prompt) == list:

+        assert(len(p.prompt) > 0)

+    else:

+        assert p.prompt is not None

+        

     devices.torch_gc()

 

     fix_seed(p)

@@ -209,7 +231,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             "Seed": all_seeds[index],

             "Face restoration": (opts.face_restoration_model if p.restore_faces else None),

             "Size": f"{p.width}x{p.height}",

-            "Model hash": (None if not opts.add_model_hash_to_info or not shared.sd_model_hash else shared.sd_model_hash),

+            "Model hash": (None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),

             "Batch size": (None if p.batch_size < 2 else p.batch_size),

             "Batch pos": (None if p.batch_size < 2 else position_in_batch),

             "Variation seed": (None if p.subseed_strength == 0 else all_subseeds[index]),

@@ -247,6 +269,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             seeds = all_seeds[n * p.batch_size:(n + 1) * p.batch_size]

             subseeds = all_subseeds[n * p.batch_size:(n + 1) * p.batch_size]

 

+            if (len(prompts) == 0):

+                break

+

             #uc = p.sd_model.get_learned_conditioning(len(prompts) * [p.negative_prompt])

             #c = p.sd_model.get_learned_conditioning(prompts)

             uc = prompt_parser.get_learned_conditioning(len(prompts) * [p.negative_prompt], p.steps)

@@ -257,7 +282,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
                     comments[comment] = 1

 

             # we manually generate all input noises because each one should have a specific seed

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

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

 

             if p.n_iter > 1:

                 shared.state.job = f"Batch {n+1} out of {p.n_iter}"

diff --git a/modules/sd_models.py b/modules/sd_models.py
new file mode 100644
index 00000000..4bd70fc5
--- /dev/null
+++ b/modules/sd_models.py
@@ -0,0 +1,148 @@
+import glob

+import os.path

+import sys

+from collections import namedtuple

+import torch

+from omegaconf import OmegaConf

+

+

+from ldm.util import instantiate_from_config

+

+from modules import shared

+

+CheckpointInfo = namedtuple("CheckpointInfo", ['filename', 'title', 'hash'])

+checkpoints_list = {}

+

+try:

+    # this silences the annoying "Some weights of the model checkpoint were not used when initializing..." message at start.

+

+    from transformers import logging

+

+    logging.set_verbosity_error()

+except Exception:

+    pass

+

+

+def list_models():

+    checkpoints_list.clear()

+

+    model_dir = os.path.abspath(shared.cmd_opts.ckpt_dir)

+

+    def modeltitle(path, h):

+        abspath = os.path.abspath(path)

+

+        if abspath.startswith(model_dir):

+            name = abspath.replace(model_dir, '')

+        else:

+            name = os.path.basename(path)

+

+        if name.startswith("\\") or name.startswith("/"):

+            name = name[1:]

+

+        return f'{name} [{h}]'

+

+    cmd_ckpt = shared.cmd_opts.ckpt

+    if os.path.exists(cmd_ckpt):

+        h = model_hash(cmd_ckpt)

+        title = modeltitle(cmd_ckpt, h)

+        checkpoints_list[title] = CheckpointInfo(cmd_ckpt, title, h)

+    elif cmd_ckpt is not None and cmd_ckpt != shared.default_sd_model_file:

+        print(f"Checkpoint in --ckpt argument not found: {cmd_ckpt}", file=sys.stderr)

+

+    if os.path.exists(model_dir):

+        for filename in glob.glob(model_dir + '/**/*.ckpt', recursive=True):

+            h = model_hash(filename)

+            title = modeltitle(filename, h)

+            checkpoints_list[title] = CheckpointInfo(filename, title, h)

+

+

+def model_hash(filename):

+    try:

+        with open(filename, "rb") as file:

+            import hashlib

+            m = hashlib.sha256()

+

+            file.seek(0x100000)

+            m.update(file.read(0x10000))

+            return m.hexdigest()[0:8]

+    except FileNotFoundError:

+        return 'NOFILE'

+

+

+def select_checkpoint():

+    model_checkpoint = shared.opts.sd_model_checkpoint

+    checkpoint_info = checkpoints_list.get(model_checkpoint, None)

+    if checkpoint_info is not None:

+        return checkpoint_info

+

+    if len(checkpoints_list) == 0:

+        print(f"Checkpoint {model_checkpoint} not found and no other checkpoints found", file=sys.stderr)

+        return None

+

+    checkpoint_info = next(iter(checkpoints_list.values()))

+    if model_checkpoint is not None:

+        print(f"Checkpoint {model_checkpoint} not found; loading fallback {checkpoint_info.title}", file=sys.stderr)

+

+    return checkpoint_info

+

+

+def load_model_weights(model, checkpoint_file, sd_model_hash):

+    print(f"Loading weights [{sd_model_hash}] from {checkpoint_file}")

+

+    pl_sd = torch.load(checkpoint_file, map_location="cpu")

+    if "global_step" in pl_sd:

+        print(f"Global Step: {pl_sd['global_step']}")

+    sd = pl_sd["state_dict"]

+

+    model.load_state_dict(sd, strict=False)

+

+    if shared.cmd_opts.opt_channelslast:

+        model.to(memory_format=torch.channels_last)

+

+    if not shared.cmd_opts.no_half:

+        model.half()

+

+    model.sd_model_hash = sd_model_hash

+    model.sd_model_checkpint = checkpoint_file

+

+

+def load_model():

+    from modules import lowvram, sd_hijack

+    checkpoint_info = select_checkpoint()

+

+    sd_config = OmegaConf.load(shared.cmd_opts.config)

+    sd_model = instantiate_from_config(sd_config.model)

+    load_model_weights(sd_model, checkpoint_info.filename, checkpoint_info.hash)

+

+    if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:

+        lowvram.setup_for_low_vram(sd_model, shared.cmd_opts.medvram)

+    else:

+        sd_model.to(shared.device)

+

+    sd_hijack.model_hijack.hijack(sd_model)

+

+    sd_model.eval()

+

+    print(f"Model loaded.")

+    return sd_model

+

+

+def reload_model_weights(sd_model, info=None):

+    from modules import lowvram, devices

+    checkpoint_info = info or select_checkpoint()

+

+    if sd_model.sd_model_checkpint == checkpoint_info.filename:

+        return

+

+    if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:

+        lowvram.send_everything_to_cpu()

+    else:

+        sd_model.to(devices.cpu)

+

+    load_model_weights(sd_model, checkpoint_info.filename, checkpoint_info.hash)

+

+    if not shared.cmd_opts.lowvram and not shared.cmd_opts.medvram:

+        sd_model.to(devices.device)

+

+    print(f"Weights loaded.")

+    return sd_model

diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py
index df3a6fe8..1b3dc302 100644
--- a/modules/sd_samplers.py
+++ b/modules/sd_samplers.py
@@ -38,6 +38,17 @@ samplers = [
 samplers_for_img2img = [x for x in samplers if x.name != 'PLMS']

 

 

+def setup_img2img_steps(p):

+    if opts.img2img_fix_steps:

+        steps = int(p.steps / min(p.denoising_strength, 0.999))

+        t_enc = p.steps - 1

+    else:

+        steps = p.steps

+        t_enc = int(min(p.denoising_strength, 0.999) * steps)

+

+    return steps, t_enc

+

+

 def sample_to_image(samples):

     x_sample = shared.sd_model.decode_first_stage(samples[0:1].type(shared.sd_model.dtype))[0]

     x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0)

@@ -80,8 +91,12 @@ class VanillaStableDiffusionSampler:
         self.mask = None

         self.nmask = None

         self.init_latent = None

+        self.sampler_noises = None

         self.step = 0

 

+    def number_of_needed_noises(self, p):

+        return 0

+

     def p_sample_ddim_hook(self, x_dec, cond, ts, unconditional_conditioning, *args, **kwargs):

         cond = prompt_parser.reconstruct_cond_batch(cond, self.step)

         unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step)

@@ -101,13 +116,13 @@ class VanillaStableDiffusionSampler:
         return res

 

     def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning):

-        t_enc = int(min(p.denoising_strength, 0.999) * p.steps)

+        steps, t_enc = setup_img2img_steps(p)

 

         # existing code fails with cetain step counts, like 9

         try:

-            self.sampler.make_schedule(ddim_num_steps=p.steps, verbose=False)

+            self.sampler.make_schedule(ddim_num_steps=steps, verbose=False)

         except Exception:

-            self.sampler.make_schedule(ddim_num_steps=p.steps+1, verbose=False)

+            self.sampler.make_schedule(ddim_num_steps=steps+1, verbose=False)

 

         x1 = self.sampler.stochastic_encode(x, torch.tensor([t_enc] * int(x.shape[0])).to(shared.device), noise=noise)

 

@@ -115,6 +130,7 @@ class VanillaStableDiffusionSampler:
         self.mask = p.mask

         self.nmask = p.nmask

         self.init_latent = p.init_latent

+        self.step = 0

 

         samples = self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning)

 

@@ -127,6 +143,7 @@ class VanillaStableDiffusionSampler:
         self.mask = None

         self.nmask = None

         self.init_latent = None

+        self.step = 0

 

         # existing code fails with cetin step counts, like 9

         try:

@@ -183,42 +200,82 @@ def extended_trange(count, *args, **kwargs):
         shared.total_tqdm.update()

 

 

+class TorchHijack:

+    def __init__(self, kdiff_sampler):

+        self.kdiff_sampler = kdiff_sampler

+

+    def __getattr__(self, item):

+        if item == 'randn_like':

+            return self.kdiff_sampler.randn_like

+

+        if hasattr(torch, item):

+            return getattr(torch, item)

+

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

+

+

 class KDiffusionSampler:

     def __init__(self, funcname, sd_model):

         self.model_wrap = k_diffusion.external.CompVisDenoiser(sd_model, quantize=shared.opts.enable_quantization)

         self.funcname = funcname

         self.func = getattr(k_diffusion.sampling, self.funcname)

         self.model_wrap_cfg = CFGDenoiser(self.model_wrap)

+        self.sampler_noises = None

+        self.sampler_noise_index = 0

 

     def callback_state(self, d):

         store_latent(d["denoised"])

 

+    def number_of_needed_noises(self, p):

+        return p.steps

+

+    def randn_like(self, x):

+        noise = self.sampler_noises[self.sampler_noise_index] if self.sampler_noises is not None and self.sampler_noise_index < len(self.sampler_noises) else None

+

+        if noise is not None and x.shape == noise.shape:

+            res = noise

+        else:

+            res = torch.randn_like(x)

+

+        self.sampler_noise_index += 1

+        return res

+

     def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning):

-        t_enc = int(min(p.denoising_strength, 0.999) * p.steps)

-        sigmas = self.model_wrap.get_sigmas(p.steps)

+        steps, t_enc = setup_img2img_steps(p)

+

+        sigmas = self.model_wrap.get_sigmas(steps)

 

-        noise = noise * sigmas[p.steps - t_enc - 1]

+        noise = noise * sigmas[steps - t_enc - 1]

 

         xi = x + noise

 

-        sigma_sched = sigmas[p.steps - t_enc - 1:]

+        sigma_sched = sigmas[steps - t_enc - 1:]

 

         self.model_wrap_cfg.mask = p.mask

         self.model_wrap_cfg.nmask = p.nmask

         self.model_wrap_cfg.init_latent = p.init_latent

+        self.model_wrap.step = 0

 

         if hasattr(k_diffusion.sampling, 'trange'):

             k_diffusion.sampling.trange = lambda *args, **kwargs: extended_trange(*args, **kwargs)

 

+        if self.sampler_noises is not None:

+            k_diffusion.sampling.torch = TorchHijack(self)

+

         return self.func(self.model_wrap_cfg, xi, sigma_sched, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state)

 

     def sample(self, p, x, conditioning, unconditional_conditioning):

         sigmas = self.model_wrap.get_sigmas(p.steps)

         x = x * sigmas[0]

 

+        self.model_wrap_cfg.step = 0

+

         if hasattr(k_diffusion.sampling, 'trange'):

             k_diffusion.sampling.trange = lambda *args, **kwargs: extended_trange(*args, **kwargs)

 

+        if self.sampler_noises is not None:

+            k_diffusion.sampling.torch = TorchHijack(self)

+

         samples_ddim = self.func(self.model_wrap_cfg, x, sigmas, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state)

         return samples_ddim

 

diff --git a/modules/shared.py b/modules/shared.py
index 78450546..3c3aa9b6 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -12,14 +12,16 @@ from modules.paths import script_path, sd_path
 from modules.devices import get_optimal_device

 import modules.styles

 import modules.interrogate

+import modules.memmon

+import modules.sd_models

 

 sd_model_file = os.path.join(script_path, 'model.ckpt')

-if not os.path.exists(sd_model_file):

-    sd_model_file = "models/ldm/stable-diffusion-v1/model.ckpt"

+default_sd_model_file = sd_model_file

 

 parser = argparse.ArgumentParser()

 parser.add_argument("--config", type=str, default=os.path.join(sd_path, "configs/stable-diffusion/v1-inference.yaml"), help="path to config which constructs model",)

-parser.add_argument("--ckpt", type=str, default=os.path.join(sd_path, sd_model_file), help="path to checkpoint of model",)

+parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; this checkpoint will be added to the list of checkpoints and loaded by default if you don't have a checkpoint selected in settings",)

+parser.add_argument("--ckpt-dir", type=str, default=os.path.join(script_path, 'models'), help="path to directory with stable diffusion checkpoints",)

 parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))

 parser.add_argument("--gfpgan-model", type=str, help="GFPGAN model file name", default='GFPGANv1.3.pth')

 parser.add_argument("--no-half", action='store_true', help="do not switch the model to 16-bit floats")

@@ -87,13 +89,17 @@ interrogator = modules.interrogate.InterrogateModels("interrogate")
 

 face_restorers = []

 

+modules.sd_models.list_models()

+

+

 class Options:

     class OptionInfo:

-        def __init__(self, default=None, label="", component=None, component_args=None):

+        def __init__(self, default=None, label="", component=None, component_args=None, onchange=None):

             self.default = default

             self.label = label

             self.component = component

             self.component_args = component_args

+            self.onchange = onchange

 

     data = None

     hide_dirs = {"visible": False} if cmd_opts.hide_ui_dir_config else None

@@ -125,9 +131,11 @@ class Options:
         "enable_pnginfo": OptionInfo(True, "Save text information about generation parameters as chunks to png files"),

         "add_model_hash_to_info": OptionInfo(False, "Add model hash to generation information"),

         "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 (normaly 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."),

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

         "enable_emphasis": OptionInfo(True, "Use (text) to make model pay more attention to text and [text] to make it pay less attention"),

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

         "save_txt": OptionInfo(False, "Create a text file next to every image with generation parameters."),

         "ESRGAN_tile": OptionInfo(192, "Tile size for upscaling. 0 = no tiling.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),

         "ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for upscaling. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}),

@@ -136,6 +144,7 @@ class Options:
         "show_progressbar": OptionInfo(True, "Show progressbar"),

         "show_progress_every_n_steps": OptionInfo(0, "Show show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}),

         "multiple_tqdm": OptionInfo(True, "Add a second progress bar to the console that shows progress for an entire job. Broken in PyCharm console."),

+        "memmon_poll_rate": OptionInfo(8, "VRAM usage polls per second during generation. Set to 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 40, "step":1}),

         "face_restoration_model": OptionInfo(None, "Face restoration model", gr.Radio, lambda: {"choices": [x.name() for x in face_restorers]}),

         "code_former_weight": OptionInfo(0.5, "CodeFormer weight parameter; 0 = maximum effect; 1 = minimum effect", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}),

         "save_images_before_face_restoration": OptionInfo(False, "Save a copy of image before doing face restoration."),

@@ -146,6 +155,7 @@ class Options:
         "interrogate_clip_min_length": OptionInfo(24, "Interrogate: minimum description length (excluding artists, etc..)", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}),

         "interrogate_clip_max_length": OptionInfo(48, "Interrogate: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}),

         "interrogate_clip_dict_limit": OptionInfo(1500, "Interrogate: maximum number of lines in text file (0 = No limit)"),

+        "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Radio, lambda: {"choices": [x.title for x in modules.sd_models.checkpoints_list.values()]}),

     }

 

     def __init__(self):

@@ -176,6 +186,10 @@ class Options:
         with open(filename, "r", encoding="utf8") as file:

             self.data = json.load(file)

 

+    def onchange(self, key, func):

+        item = self.data_labels.get(key)

+        item.onchange = func

+

 

 opts = Options()

 if os.path.exists(config_filename):

@@ -184,7 +198,6 @@ if os.path.exists(config_filename):
 sd_upscalers = []

 

 sd_model = None

-sd_model_hash = ''

 

 progress_print_out = sys.stdout

 

@@ -215,3 +228,6 @@ class TotalTQDM:
 

 

 total_tqdm = TotalTQDM()

+

+mem_mon = modules.memmon.MemUsageMonitor("MemMon", device, opts)

+mem_mon.start()

diff --git a/modules/ui.py b/modules/ui.py
index b6d5dcd8..2f6eb307 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -119,6 +119,7 @@ def save_files(js_data, images, index):
 

 def wrap_gradio_call(func):

     def f(*args, **kwargs):

+        shared.mem_mon.monitor()

         t = time.perf_counter()

 

         try:

@@ -135,8 +136,20 @@ def wrap_gradio_call(func):
 

         elapsed = time.perf_counter() - t

 

+        mem_stats = {k: -(v//-(1024*1024)) for k,v in shared.mem_mon.stop().items()}

+        active_peak = mem_stats['active_peak']

+        reserved_peak = mem_stats['reserved_peak']

+        sys_peak = '?' if opts.memmon_poll_rate <= 0 else mem_stats['system_peak']

+        sys_total = mem_stats['total']

+        sys_pct = '?' if opts.memmon_poll_rate <= 0 else round(sys_peak/sys_total * 100, 2)

+        vram_tooltip = "Torch active: Peak amount of VRAM used by Torch during generation, excluding cached data.&#013;" \

+                       "Torch reserved: Peak amount of VRAM allocated by Torch, including all active and cached data.&#013;" \

+                       "Sys VRAM: Peak amount of VRAM allocation across all applications / total GPU VRAM (peak utilization%)."

+

+        vram_html = '' if opts.memmon_poll_rate == 0 else f"<p class='vram' title='{vram_tooltip}'>Torch active/reserved: {active_peak}/{reserved_peak} MiB, <wbr>Sys VRAM: {sys_peak}/{sys_total} MiB ({sys_pct}%)</p>"

+

         # last item is always HTML

-        res[-1] = res[-1] + f"<p class='performance'>Time taken: {elapsed:.2f}s</p>"

+        res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr>{elapsed:.2f}s</p>{vram_html}</div>"

 

         shared.state.interrupted = False

 

@@ -324,6 +337,8 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                     custom_inputs = modules.scripts.scripts_txt2img.setup_ui(is_img2img=False)

 

             with gr.Column(variant='panel'):

+                progressbar = gr.HTML(elem_id="progressbar")

+

                 with gr.Group():

                     txt2img_preview = gr.Image(elem_id='txt2img_preview', visible=False)

                     txt2img_gallery = gr.Gallery(label='Output', elem_id='txt2img_gallery').style(grid=4)

@@ -336,8 +351,6 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                         send_to_extras = gr.Button('Send to extras')

                         interrupt = gr.Button('Interrupt')

 

-                progressbar = gr.HTML(elem_id="progressbar")

-

                 with gr.Group():

                     html_info = gr.HTML()

                     generation_info = gr.Textbox(visible=False)

@@ -461,6 +474,8 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                     custom_inputs = modules.scripts.scripts_img2img.setup_ui(is_img2img=True)

 

             with gr.Column(variant='panel'):

+                progressbar = gr.HTML(elem_id="progressbar")

+

                 with gr.Group():

                     img2img_preview = gr.Image(elem_id='img2img_preview', visible=False)

                     img2img_gallery = gr.Gallery(label='Output', elem_id='img2img_gallery').style(grid=4)

@@ -474,7 +489,6 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                         interrupt = gr.Button('Interrupt')

                         img2img_save_style = gr.Button('Save prompt as style')

 

-                progressbar = gr.HTML(elem_id="progressbar")

 

                 with gr.Group():

                     html_info = gr.HTML()

@@ -649,7 +663,7 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                         image = gr.Image(label="Source", source="upload", interactive=True, type="pil")

 

                     with gr.TabItem('Batch Process'):

-                        image_batch = gr.File(label="Batch Process", file_count="multiple", source="upload", interactive=True, type="file")

+                        image_batch = gr.File(label="Batch Process", file_count="multiple", interactive=True, type="file")

 

                 upscaling_resize = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Resize", value=2)

 

@@ -745,7 +759,12 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
             if comp_args and isinstance(comp_args, dict) and comp_args.get('visible') is False:

                 continue

 

+            oldval = opts.data.get(key, None)

             opts.data[key] = value

+

+            if oldval != value and opts.data_labels[key].onchange is not None:

+                opts.data_labels[key].onchange()

+

             up.append(comp.update(value=value))

 

         opts.save(shared.config_filename)

@@ -782,6 +801,11 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
     with open(os.path.join(script_path, "style.css"), "r", encoding="utf8") as file:

         css = file.read()

 

+    if os.path.exists(os.path.join(script_path, "user.css")):

+        with open(os.path.join(script_path, "user.css"), "r", encoding="utf8") as file:

+            usercss = file.read()

+            css += usercss

+

     if not cmd_opts.no_progressbar_hiding:

         css += css_hide_progressbar

 

diff --git a/script.js b/script.js
index 0852e421..113d4335 100644
--- a/script.js
+++ b/script.js
@@ -66,6 +66,8 @@ titles = {
     "Style 2": "Style to apply; styles have components for both positive and negative prompts and apply to both",
     "Apply style": "Insert selected styles into prompt fields",
     "Create style": "Save current prompts as a style. If you add the token {prompt} to the text, the style use that as placeholder for your prompt when you use the style in the future.",
+
+    "Checkpoint name": "Loads weights from checkpoint before making images. You can either use hash or a part of filename (as seen in settings) for checkpoint name. Recommended to use with Y axis for less switching.",
 }
 
 function gradioApp(){
@@ -74,6 +76,90 @@ function gradioApp(){
 
 global_progressbar = null
 
+function closeModal() {
+  gradioApp().getElementById("lightboxModal").style.display = "none";
+}
+
+function showModal(event) {
+  var source = event.target || event.srcElement;
+  gradioApp().getElementById("modalImage").src = source.src
+  var lb = gradioApp().getElementById("lightboxModal")
+  lb.style.display = "block";
+  lb.focus()
+  event.stopPropagation()
+}
+
+function negmod(n, m) {
+  return ((n % m) + m) % m;
+}
+
+function modalImageSwitch(offset){
+  var galleryButtons = gradioApp().querySelectorAll(".gallery-item.transition-all")
+
+  if(galleryButtons.length>1){
+      var currentButton  = gradioApp().querySelector(".gallery-item.transition-all.\\!ring-2")
+
+      var result = -1
+      galleryButtons.forEach(function(v, i){ if(v==currentButton) { result = i } })
+
+      if(result != -1){
+        nextButton = galleryButtons[negmod((result+offset),galleryButtons.length)]
+        nextButton.click()
+        gradioApp().getElementById("modalImage").src = nextButton.children[0].src
+        setTimeout( function(){gradioApp().getElementById("lightboxModal").focus()},10)
+      }
+  }
+
+}
+
+function modalNextImage(event){
+  modalImageSwitch(1)
+  event.stopPropagation()
+}
+
+function modalPrevImage(event){
+  modalImageSwitch(-1)  
+  event.stopPropagation()
+}
+
+function modalKeyHandler(event){
+    switch (event.key) {
+        case "ArrowLeft":
+            modalPrevImage(event)
+            break;
+        case "ArrowRight":
+            modalNextImage(event)
+            break;
+    }
+}
+
+function showGalleryImage(){
+    setTimeout(function() {
+        fullImg_preview = gradioApp().querySelectorAll('img.w-full.object-contain')
+        
+        if(fullImg_preview != null){
+            fullImg_preview.forEach(function function_name(e) {
+                if(e && e.parentElement.tagName == 'DIV'){
+
+                    e.style.cursor='pointer'
+
+                    e.addEventListener('click', function (evt) {
+                      showModal(evt)
+
+                    },true);
+                }
+            });
+        }
+
+    }, 100);
+}
+
+function galleryImageHandler(e){
+    if(e && e.parentElement.tagName == 'BUTTON'){
+        e.onclick = showGalleryImage;
+    }
+}
+
 function addTitles(root){
 	root.querySelectorAll('span, button, select').forEach(function(span){
 		tooltip = titles[span.textContent];
@@ -115,13 +201,18 @@ function addTitles(root){
                 img2img_preview.style.width = img2img_gallery.clientWidth + "px"
                 img2img_preview.style.height = img2img_gallery.clientHeight + "px"
             }
-
-
+		
             window.setTimeout(requestProgress, 500)
         });
         mutationObserver.observe( progressbar, { childList:true, subtree:true })
 	}
+	
+	fullImg_preview = gradioApp().querySelectorAll('img.w-full')
 
+	    if(fullImg_preview != null){
+		fullImg_preview.forEach(galleryImageHandler);
+	}
+	
 }
 
 document.addEventListener("DOMContentLoaded", function() {
@@ -129,6 +220,49 @@ document.addEventListener("DOMContentLoaded", function() {
         addTitles(gradioApp());
     });
     mutationObserver.observe( gradioApp(), { childList:true, subtree:true })
+	
+    const modalFragment = document.createDocumentFragment();
+    const modal = document.createElement('div')
+    modal.onclick = closeModal;
+    
+    const modalClose = document.createElement('span')
+    modalClose.className = 'modalClose cursor';
+    modalClose.innerHTML = '&times;'
+    modalClose.onclick = closeModal;
+    modal.id = "lightboxModal";
+    modal.tabIndex=0
+    modal.addEventListener('keydown', modalKeyHandler, true)
+    modal.appendChild(modalClose)
+
+    const modalImage = document.createElement('img')
+    modalImage.id = 'modalImage';
+    modalImage.onclick = closeModal;
+    modalImage.tabIndex=0
+    modalImage.addEventListener('keydown', modalKeyHandler, true)
+    modal.appendChild(modalImage)
+
+    const modalPrev = document.createElement('a')
+    modalPrev.className = 'modalPrev';
+    modalPrev.innerHTML = '&#10094;'
+    modalPrev.tabIndex=0
+    modalPrev.addEventListener('click',modalPrevImage,true);
+    modalPrev.addEventListener('keydown', modalKeyHandler, true)
+    modal.appendChild(modalPrev)
+
+    const modalNext = document.createElement('a')
+    modalNext.className = 'modalNext';
+    modalNext.innerHTML = '&#10095;'
+    modalNext.tabIndex=0
+    modalNext.addEventListener('click',modalNextImage,true);
+    modalNext.addEventListener('keydown', modalKeyHandler, true)
+
+    modal.appendChild(modalNext)
+
+
+    gradioApp().getRootNode().appendChild(modal)
+    
+    document.body.appendChild(modalFragment);
+	
 });
 
 function selected_gallery_index(){
@@ -180,6 +314,15 @@ function submit(){
     for(var i=0;i<arguments.length;i++){
         res.push(arguments[i])
     }
+
+    // As it is currently, txt2img and img2img send back the previous output args (txt2img_gallery, generation_info, html_info) whenever you generate a new image.
+    // This can lead to uploading a huge gallery of previously generated images, which leads to an unnecessary delay between submitting and beginning to generate.
+    // I don't know why gradio is seding outputs along with inputs, but we can prevent sending the image gallery here, which seems to be an issue for some.
+    // If gradio at some point stops sending outputs, this may break something
+    if(Array.isArray(res[res.length - 3])){
+        res[res.length - 3] = null
+    }
+
     return res
 }
 
diff --git a/scripts/img2imgalt.py b/scripts/img2imgalt.py
index 7813bbcc..7f1f53a7 100644
--- a/scripts/img2imgalt.py
+++ b/scripts/img2imgalt.py
@@ -59,7 +59,7 @@ def find_noise_for_image(p, cond, uncond, cfg_scale, steps):
     return x / x.std()

 

 

-Cached = namedtuple("Cached", ["noise", "cfg_scale", "steps", "latent", "original_prompt"])

+Cached = namedtuple("Cached", ["noise", "cfg_scale", "steps", "latent", "original_prompt", "original_negative_prompt"])

 

 

 class Script(scripts.Script):

@@ -74,34 +74,45 @@ class Script(scripts.Script):
 

     def ui(self, is_img2img):

         original_prompt = gr.Textbox(label="Original prompt", lines=1)

+        original_negative_prompt = gr.Textbox(label="Original negative prompt", lines=1)

         cfg = gr.Slider(label="Decode CFG scale", minimum=0.0, maximum=15.0, step=0.1, value=1.0)

         st = gr.Slider(label="Decode steps", minimum=1, maximum=150, step=1, value=50)

+        randomness = gr.Slider(label="randomness", minimum=0.0, maximum=1.0, step=0.01, value=0.0)

+        return [original_prompt, original_negative_prompt, cfg, st, randomness]

 

-        return [original_prompt, cfg, st]

-

-    def run(self, p, original_prompt, cfg, st):

+    def run(self, p, original_prompt, original_negative_prompt, cfg, st, randomness):

         p.batch_size = 1

         p.batch_count = 1

 

         def sample_extra(x, conditioning, unconditional_conditioning):

             lat = (p.init_latent.cpu().numpy() * 10).astype(int)

 

-            same_params = self.cache is not None and self.cache.cfg_scale == cfg and self.cache.steps == st and self.cache.original_prompt == original_prompt

+            same_params = self.cache is not None and self.cache.cfg_scale == cfg and self.cache.steps == st and self.cache.original_prompt == original_prompt and self.cache.original_negative_prompt == original_negative_prompt

             same_everything = same_params and self.cache.latent.shape == lat.shape and np.abs(self.cache.latent-lat).sum() < 100

 

             if same_everything:

-                noise = self.cache.noise

+                rec_noise = self.cache.noise

             else:

                 shared.state.job_count += 1

                 cond = p.sd_model.get_learned_conditioning(p.batch_size * [original_prompt])

-                uncond = p.sd_model.get_learned_conditioning(p.batch_size * [""])

-                noise = find_noise_for_image(p, cond, uncond, cfg, st)

-                self.cache = Cached(noise, cfg, st, lat, original_prompt)

-

+                uncond = p.sd_model.get_learned_conditioning(p.batch_size * [original_negative_prompt])

+                rec_noise = find_noise_for_image(p, cond, uncond, cfg, st)

+                self.cache = Cached(rec_noise, cfg, st, lat, original_prompt, original_negative_prompt)

+

+            rand_noise = processing.create_random_tensors(p.init_latent.shape[1:], [p.seed + x + 1 for x in range(p.init_latent.shape[0])])

+            

+            combined_noise = ((1 - randomness) * rec_noise + randomness * rand_noise) / ((randomness**2 + (1-randomness)**2) ** 0.5)

+            

             sampler = samplers[p.sampler_index].constructor(p.sd_model)

 

-            samples_ddim = sampler.sample(p, noise, conditioning, unconditional_conditioning)

-            return samples_ddim

+            sigmas = sampler.model_wrap.get_sigmas(p.steps)

+            

+            noise_dt = combined_noise - ( p.init_latent / sigmas[0] )

+            

+            p.seed = p.seed + 1

+            

+            return sampler.sample_img2img(p, p.init_latent, noise_dt, conditioning, unconditional_conditioning)

+

 

         p.sample = sample_extra

 

diff --git a/scripts/outpainting_mk_2.py b/scripts/outpainting_mk_2.py
new file mode 100644
index 00000000..a42c1aed
--- /dev/null
+++ b/scripts/outpainting_mk_2.py
@@ -0,0 +1,290 @@
+import math

+

+import numpy as np

+import skimage

+

+import modules.scripts as scripts

+import gradio as gr

+from PIL import Image, ImageDraw

+

+from modules import images, processing, devices

+from modules.processing import Processed, process_images

+from modules.shared import opts, cmd_opts, state

+

+

+def expand(x, dir, amount, power=0.75):

+    is_left = dir == 3

+    is_right = dir == 1

+    is_up = dir == 0

+    is_down = dir == 2

+

+    if is_left or is_right:

+        noise = np.zeros((x.shape[0], amount, 3), dtype=float)

+        indexes = np.random.random((x.shape[0], amount)) ** power * (1 - np.arange(amount) / amount)

+        if is_right:

+            indexes = 1 - indexes

+        indexes = (indexes * (x.shape[1] - 1)).astype(int)

+

+        for row in range(x.shape[0]):

+            if is_left:

+                noise[row] = x[row][indexes[row]]

+            else:

+                noise[row] = np.flip(x[row][indexes[row]], axis=0)

+

+        x = np.concatenate([noise, x] if is_left else [x, noise], axis=1)

+        return x

+

+    if is_up or is_down:

+        noise = np.zeros((amount, x.shape[1], 3), dtype=float)

+        indexes = np.random.random((x.shape[1], amount)) ** power * (1 - np.arange(amount) / amount)

+        if is_down:

+            indexes = 1 - indexes

+        indexes = (indexes * x.shape[0] - 1).astype(int)

+

+        for row in range(x.shape[1]):

+            if is_up:

+                noise[:, row] = x[:, row][indexes[row]]

+            else:

+                noise[:, row] = np.flip(x[:, row][indexes[row]], axis=0)

+

+        x = np.concatenate([noise, x] if is_up else [x, noise], axis=0)

+        return x

+

+

+def get_matched_noise(_np_src_image, np_mask_rgb, noise_q=1, color_variation=0.05):

+    # helper fft routines that keep ortho normalization and auto-shift before and after fft

+    def _fft2(data):

+        if data.ndim > 2:  # has channels

+            out_fft = np.zeros((data.shape[0], data.shape[1], data.shape[2]), dtype=np.complex128)

+            for c in range(data.shape[2]):

+                c_data = data[:, :, c]

+                out_fft[:, :, c] = np.fft.fft2(np.fft.fftshift(c_data), norm="ortho")

+                out_fft[:, :, c] = np.fft.ifftshift(out_fft[:, :, c])

+        else:  # one channel

+            out_fft = np.zeros((data.shape[0], data.shape[1]), dtype=np.complex128)

+            out_fft[:, :] = np.fft.fft2(np.fft.fftshift(data), norm="ortho")

+            out_fft[:, :] = np.fft.ifftshift(out_fft[:, :])

+

+        return out_fft

+

+    def _ifft2(data):

+        if data.ndim > 2:  # has channels

+            out_ifft = np.zeros((data.shape[0], data.shape[1], data.shape[2]), dtype=np.complex128)

+            for c in range(data.shape[2]):

+                c_data = data[:, :, c]

+                out_ifft[:, :, c] = np.fft.ifft2(np.fft.fftshift(c_data), norm="ortho")

+                out_ifft[:, :, c] = np.fft.ifftshift(out_ifft[:, :, c])

+        else:  # one channel

+            out_ifft = np.zeros((data.shape[0], data.shape[1]), dtype=np.complex128)

+            out_ifft[:, :] = np.fft.ifft2(np.fft.fftshift(data), norm="ortho")

+            out_ifft[:, :] = np.fft.ifftshift(out_ifft[:, :])

+

+        return out_ifft

+

+    def _get_gaussian_window(width, height, std=3.14, mode=0):

+        window_scale_x = float(width / min(width, height))

+        window_scale_y = float(height / min(width, height))

+

+        window = np.zeros((width, height))

+        x = (np.arange(width) / width * 2. - 1.) * window_scale_x

+        for y in range(height):

+            fy = (y / height * 2. - 1.) * window_scale_y

+            if mode == 0:

+                window[:, y] = np.exp(-(x ** 2 + fy ** 2) * std)

+            else:

+                window[:, y] = (1 / ((x ** 2 + 1.) * (fy ** 2 + 1.))) ** (std / 3.14)  # hey wait a minute that's not gaussian

+

+        return window

+

+    def _get_masked_window_rgb(np_mask_grey, hardness=1.):

+        np_mask_rgb = np.zeros((np_mask_grey.shape[0], np_mask_grey.shape[1], 3))

+        if hardness != 1.:

+            hardened = np_mask_grey[:] ** hardness

+        else:

+            hardened = np_mask_grey[:]

+        for c in range(3):

+            np_mask_rgb[:, :, c] = hardened[:]

+        return np_mask_rgb

+

+    width = _np_src_image.shape[0]

+    height = _np_src_image.shape[1]

+    num_channels = _np_src_image.shape[2]

+

+    np_src_image = _np_src_image[:] * (1. - np_mask_rgb)

+    np_mask_grey = (np.sum(np_mask_rgb, axis=2) / 3.)

+    img_mask = np_mask_grey > 1e-6

+    ref_mask = np_mask_grey < 1e-3

+

+    windowed_image = _np_src_image * (1. - _get_masked_window_rgb(np_mask_grey))

+    windowed_image /= np.max(windowed_image)

+    windowed_image += np.average(_np_src_image) * np_mask_rgb  # / (1.-np.average(np_mask_rgb))  # rather than leave the masked area black, we get better results from fft by filling the average unmasked color

+

+    src_fft = _fft2(windowed_image)  # get feature statistics from masked src img

+    src_dist = np.absolute(src_fft)

+    src_phase = src_fft / src_dist

+

+    noise_window = _get_gaussian_window(width, height, mode=1)  # start with simple gaussian noise

+    noise_rgb = np.random.random_sample((width, height, num_channels))

+    noise_grey = (np.sum(noise_rgb, axis=2) / 3.)

+    noise_rgb *= color_variation  # the colorfulness of the starting noise is blended to greyscale with a parameter

+    for c in range(num_channels):

+        noise_rgb[:, :, c] += (1. - color_variation) * noise_grey

+

+    noise_fft = _fft2(noise_rgb)

+    for c in range(num_channels):

+        noise_fft[:, :, c] *= noise_window

+    noise_rgb = np.real(_ifft2(noise_fft))

+    shaped_noise_fft = _fft2(noise_rgb)

+    shaped_noise_fft[:, :, :] = np.absolute(shaped_noise_fft[:, :, :]) ** 2 * (src_dist ** noise_q) * src_phase  # perform the actual shaping

+

+    brightness_variation = 0.  # color_variation # todo: temporarily tieing brightness variation to color variation for now

+    contrast_adjusted_np_src = _np_src_image[:] * (brightness_variation + 1.) - brightness_variation * 2.

+

+    # scikit-image is used for histogram matching, very convenient!

+    shaped_noise = np.real(_ifft2(shaped_noise_fft))

+    shaped_noise -= np.min(shaped_noise)

+    shaped_noise /= np.max(shaped_noise)

+    shaped_noise[img_mask, :] = skimage.exposure.match_histograms(shaped_noise[img_mask, :] ** 1., contrast_adjusted_np_src[ref_mask, :], channel_axis=1)

+    shaped_noise = _np_src_image[:] * (1. - np_mask_rgb) + shaped_noise * np_mask_rgb

+

+    matched_noise = shaped_noise[:]

+

+    return np.clip(matched_noise, 0., 1.)

+

+

+

+class Script(scripts.Script):

+    def title(self):

+        return "Outpainting mk2"

+

+    def show(self, is_img2img):

+        return is_img2img

+

+    def ui(self, is_img2img):

+        if not is_img2img:

+            return None

+

+        info = gr.HTML("<p style=\"margin-bottom:0.75em\">Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8</p>")

+

+        pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128)

+        mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=8, visible=False)

+        direction = gr.CheckboxGroup(label="Outpainting direction", choices=['left', 'right', 'up', 'down'], value=['left', 'right', 'up', 'down'])

+        noise_q = gr.Slider(label="Fall-off exponent (lower=higher detail)", minimum=0.0, maximum=4.0, step=0.01, value=1.0)

+        color_variation = gr.Slider(label="Color variation", minimum=0.0, maximum=1.0, step=0.01, value=0.05)

+

+        return [info, pixels, mask_blur, direction, noise_q, color_variation]

+

+    def run(self, p, _, pixels, mask_blur, direction, noise_q, color_variation):

+        initial_seed_and_info = [None, None]

+

+        process_width = p.width

+        process_height = p.height

+

+        p.mask_blur = mask_blur*4

+        p.inpaint_full_res = False

+        p.inpainting_fill = 1

+        p.do_not_save_samples = True

+        p.do_not_save_grid = True

+

+        left = pixels if "left" in direction else 0

+        right = pixels if "right" in direction else 0

+        up = pixels if "up" in direction else 0

+        down = pixels if "down" in direction else 0

+

+        init_img = p.init_images[0]

+        target_w = math.ceil((init_img.width + left + right) / 64) * 64

+        target_h = math.ceil((init_img.height + up + down) / 64) * 64

+

+        if left > 0:

+            left = left * (target_w - init_img.width) // (left + right)

+        if right > 0:

+            right = target_w - init_img.width - left

+

+        if up > 0:

+            up = up * (target_h - init_img.height) // (up + down)

+

+        if down > 0:

+            down = target_h - init_img.height - up

+

+        init_image = p.init_images[0]

+

+        state.job_count = (1 if left > 0 else 0) + (1 if right > 0 else 0)+ (1 if up > 0 else 0)+ (1 if down > 0 else 0)

+

+        def expand(init, expand_pixels, is_left=False, is_right=False, is_top=False, is_bottom=False):

+            is_horiz = is_left or is_right

+            is_vert = is_top or is_bottom

+            pixels_horiz = expand_pixels if is_horiz else 0

+            pixels_vert = expand_pixels if is_vert else 0

+

+            img = Image.new("RGB", (init.width + pixels_horiz, init.height + pixels_vert))

+            img.paste(init, (pixels_horiz if is_left else 0, pixels_vert if is_top else 0))

+            mask = Image.new("RGB", (init.width + pixels_horiz, init.height + pixels_vert), "white")

+            draw = ImageDraw.Draw(mask)

+            draw.rectangle((

+                expand_pixels + mask_blur if is_left else 0,

+                expand_pixels + mask_blur if is_top else 0,

+                mask.width - expand_pixels - mask_blur if is_right else mask.width,

+                mask.height - expand_pixels - mask_blur if is_bottom else mask.height,

+            ), fill="black")

+

+            np_image = (np.asarray(img) / 255.0).astype(np.float64)

+            np_mask = (np.asarray(mask) / 255.0).astype(np.float64)

+            noised = get_matched_noise(np_image, np_mask, noise_q, color_variation)

+            out = Image.fromarray(np.clip(noised * 255., 0., 255.).astype(np.uint8), mode="RGB")

+

+            target_width = min(process_width, init.width + pixels_horiz) if is_horiz else img.width

+            target_height = min(process_height, init.height + pixels_vert) if is_vert else img.height

+

+            crop_region = (

+                0 if is_left else out.width - target_width,

+                0 if is_top else out.height - target_height,

+                target_width if is_left else out.width,

+                target_height if is_top else out.height,

+            )

+

+            image_to_process = out.crop(crop_region)

+            mask = mask.crop(crop_region)

+

+            p.width = target_width if is_horiz else img.width

+            p.height = target_height if is_vert else img.height

+            p.init_images = [image_to_process]

+            p.image_mask = mask

+

+            latent_mask = Image.new("RGB", (p.width, p.height), "white")

+            draw = ImageDraw.Draw(latent_mask)

+            draw.rectangle((

+                expand_pixels + mask_blur * 2 if is_left else 0,

+                expand_pixels + mask_blur * 2 if is_top else 0,

+                mask.width - expand_pixels - mask_blur * 2 if is_right else mask.width,

+                mask.height - expand_pixels - mask_blur * 2 if is_bottom else mask.height,

+            ), fill="black")

+            p.latent_mask = latent_mask

+

+            proc = process_images(p)

+            proc_img = proc.images[0]

+

+            if initial_seed_and_info[0] is None:

+                initial_seed_and_info[0] = proc.seed

+                initial_seed_and_info[1] = proc.info

+

+            out.paste(proc_img, (0 if is_left else out.width - proc_img.width, 0 if is_top else out.height - proc_img.height))

+            return out

+

+        img = init_image

+

+        if left > 0:

+            img = expand(img, left, is_left=True)

+        if right > 0:

+            img = expand(img, right, is_right=True)

+        if up > 0:

+            img = expand(img, up, is_top=True)

+        if down > 0:

+            img = expand(img, down, is_bottom=True)

+

+        res = Processed(p, [img], initial_seed_and_info[0], initial_seed_and_info[1])

+

+        if opts.samples_save:

+            images.save_image(img, p.outpath_samples, "", res.seed, p.prompt, opts.grid_format, info=res.info, p=p)

+

+        return res

+

diff --git a/scripts/prompts_from_file.py b/scripts/prompts_from_file.py
index d9b01c81..513d9a1c 100644
--- a/scripts/prompts_from_file.py
+++ b/scripts/prompts_from_file.py
@@ -13,28 +13,42 @@ from modules.shared import opts, cmd_opts, state
 

 class Script(scripts.Script):

     def title(self):

-        return "Prompts from file"

+        return "Prompts from file or textbox"

 

     def ui(self, is_img2img):

+        # This checkbox would look nicer as two tabs, but there are two problems:

+        # 1) There is a bug in Gradio 3.3 that prevents visibility from working on Tabs

+        # 2) Even with Gradio 3.3.1, returning a control (like Tabs) that can't be used as input

+        #    causes a AttributeError: 'Tabs' object has no attribute 'preprocess' assert,

+        #    due to the way Script assumes all controls returned can be used as inputs.

+        # Therefore, there's no good way to use grouping components right now,

+        # so we will use a checkbox! :)

+        checkbox_txt = gr.Checkbox(label="Show Textbox", value=False)

         file = gr.File(label="File with inputs", type='bytes')

-

-        return [file]

-

-    def run(self, p, data: bytes):

-        lines = [x.strip() for x in data.decode('utf8', errors='ignore').split("\n")]

+        prompt_txt = gr.TextArea(label="Prompts")

+        checkbox_txt.change(fn=lambda x: [gr.File.update(visible = not x), gr.TextArea.update(visible = x)], inputs=[checkbox_txt], outputs=[file, prompt_txt])

+        return [checkbox_txt, file, prompt_txt]

+

+    def run(self, p, checkbox_txt, data: bytes, prompt_txt: str):

+        if (checkbox_txt):

+            lines = [x.strip() for x in prompt_txt.splitlines()]

+        else:

+            lines = [x.strip() for x in data.decode('utf8', errors='ignore').split("\n")]

         lines = [x for x in lines if len(x) > 0]

 

-        batch_count = math.ceil(len(lines) / p.batch_size)

-        print(f"Will process {len(lines) * p.n_iter} images in {batch_count * p.n_iter} batches.")

+        img_count = len(lines) * p.n_iter

+        batch_count = math.ceil(img_count / p.batch_size)

+        loop_count = math.ceil(batch_count / p.n_iter)

+        print(f"Will process {img_count} images in {batch_count} batches.")

 

         p.do_not_save_grid = True

 

         state.job_count = batch_count

 

         images = []

-        for batch_no in range(batch_count):

-            state.job = f"{batch_no + 1} out of {batch_count * p.n_iter}"

-            p.prompt = lines[batch_no*p.batch_size:(batch_no+1)*p.batch_size] * p.n_iter

+        for loop_no in range(loop_count):

+            state.job = f"{loop_no + 1} out of {loop_count}"

+            p.prompt = lines[loop_no*p.batch_size:(loop_no+1)*p.batch_size] * p.n_iter

             proc = process_images(p)

             images += proc.images

 

diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py
index eccfda87..6a157722 100644
--- a/scripts/xy_grid.py
+++ b/scripts/xy_grid.py
@@ -10,7 +10,9 @@ import gradio as gr
 from modules import images

 from modules.processing import process_images, Processed

 from modules.shared import opts, cmd_opts, state

+import modules.shared as shared

 import modules.sd_samplers

+import modules.sd_models

 import re

 

 

@@ -41,6 +43,15 @@ def apply_sampler(p, x, xs):
     p.sampler_index = sampler_index

 

 

+def apply_checkpoint(p, x, xs):

+    applicable = [info for info in modules.sd_models.checkpoints_list.values() if x in info.title]

+    assert len(applicable) > 0, f'Checkpoint {x} for found'

+

+    info = applicable[0]

+

+    modules.sd_models.reload_model_weights(shared.sd_model, info)

+

+

 def format_value_add_label(p, opt, x):

     if type(x) == float:

         x = round(x, 8)

@@ -74,15 +85,16 @@ axis_options = [
     AxisOption("CFG Scale", float, apply_field("cfg_scale"), format_value_add_label),

     AxisOption("Prompt S/R", str, apply_prompt, format_value),

     AxisOption("Sampler", str, apply_sampler, format_value),

+    AxisOption("Checkpoint name", str, apply_checkpoint, format_value),

     AxisOptionImg2Img("Denoising", float, apply_field("denoising_strength"), format_value_add_label), #  as it is now all AxisOptionImg2Img items must go after AxisOption ones

 ]

 

 

-def draw_xy_grid(p, xs, ys, x_label, y_label, cell, draw_legend):

+def draw_xy_grid(p, xs, ys, x_labels, y_labels, cell, draw_legend):

     res = []

 

-    ver_texts = [[images.GridAnnotation(y_label(y))] for y in ys]

-    hor_texts = [[images.GridAnnotation(x_label(x))] for x in xs]

+    ver_texts = [[images.GridAnnotation(y)] for y in y_labels]

+    hor_texts = [[images.GridAnnotation(x)] for x in x_labels]

 

     first_pocessed = None

 

@@ -206,8 +218,8 @@ class Script(scripts.Script):
             p,

             xs=xs,

             ys=ys,

-            x_label=lambda x: x_opt.format_value(p, x_opt, x),

-            y_label=lambda y: y_opt.format_value(p, y_opt, y),

+            x_labels=[x_opt.format_value(p, x_opt, x) for x in xs],

+            y_labels=[y_opt.format_value(p, y_opt, y) for y in ys],

             cell=cell,

             draw_legend=draw_legend

         )

@@ -215,4 +227,7 @@ class Script(scripts.Script):
         if opts.grid_save:

             images.save_image(processed.images[0], p.outpath_grids, "xy_grid", prompt=p.prompt, seed=processed.seed, grid=True, p=p)

 

+        # restore checkpoint in case it was changed by axes

+        modules.sd_models.reload_model_weights(shared.sd_model)

+

         return processed

diff --git a/style.css b/style.css
index d41c098c..26c759d7 100644
--- a/style.css
+++ b/style.css
@@ -1,17 +1,48 @@
 .output-html p {margin: 0 0.5em;}

-.performance { font-size: 0.85em; color: #444; }

+

+.performance {

+    font-size: 0.85em;

+    color: #444;

+    display: flex;

+    justify-content: space-between;

+    white-space: nowrap;

+}

+

+.performance .time {

+    margin-right: 0;

+}

+

+.performance .vram {

+    margin-left: 0;

+    text-align: right;

+}

 

 #generate{

     min-height: 4.5em;

 }

 

-#txt2img_gallery, #img2img_gallery{

-    min-height: 768px;

+@media screen and (min-width: 2500px) {

+    #txt2img_gallery, #img2img_gallery {

+        min-height: 768px;

+    }

 }

+

 #txt2img_gallery img, #img2img_gallery img{

     object-fit: scale-down;

 }

 

+.justify-center.overflow-x-scroll {

+    justify-content: left;

+}

+

+.justify-center.overflow-x-scroll button:first-of-type {

+    margin-left: auto;

+}

+

+.justify-center.overflow-x-scroll button:last-of-type {

+    margin-right: auto;

+}

+

 #subseed_show{

     min-width: 6em;

     max-width: 6em;

@@ -151,6 +182,12 @@ input[type="range"]{
 #txt2img_negative_prompt, #img2img_negative_prompt{

 }

 

+#progressbar{

+  position: absolute;

+  z-index: 1000;

+  right: 0;

+}

+

 .progressDiv{

   width: 100%;

   height: 30px;

@@ -174,3 +211,66 @@ input[type="range"]{
   border-radius: 8px;

 }

 

+#lightboxModal{

+  display: none;

+  position: fixed;

+  z-index: 900;

+  padding-top: 100px;

+  left: 0;

+  top: 0;

+  width: 100%;

+  height: 100%;

+  overflow: auto;

+  background-color: rgba(20, 20, 20, 0.95);

+}

+

+.modalClose {

+  color: white;

+  position: absolute;

+  top: 10px;

+  right: 25px;

+  font-size: 35px;

+  font-weight: bold;

+}

+

+.modalClose:hover,

+.modalClose:focus {

+  color: #999;

+  text-decoration: none;

+  cursor: pointer;

+}

+

+#modalImage {

+    display: block;

+    margin-left: auto;

+    margin-right: auto;

+    margin-top: auto;

+    width: auto;

+}

+

+.modalPrev,

+.modalNext {

+  cursor: pointer;

+  position: absolute;

+  top: 50%;

+  width: auto;

+  padding: 16px;

+  margin-top: -50px;

+  color: white;

+  font-weight: bold;

+  font-size: 20px;

+  transition: 0.6s ease;

+  border-radius: 0 3px 3px 0;

+  user-select: none;

+  -webkit-user-select: none;

+}

+

+.modalNext {

+  right: 0;

+  border-radius: 3px 0 0 3px;

+}

+

+.modalPrev:hover,

+.modalNext:hover {

+  background-color: rgba(0, 0, 0, 0.8);

+}

diff --git a/webui.py b/webui.py
index add72123..ff8997db 100644
--- a/webui.py
+++ b/webui.py
@@ -3,13 +3,8 @@ import threading
 

 from modules.paths import script_path

 

-import torch

-from omegaconf import OmegaConf

-

 import signal

 

-from ldm.util import instantiate_from_config

-

 from modules.shared import opts, cmd_opts, state

 import modules.shared as shared

 import modules.ui

@@ -24,6 +19,7 @@ import modules.extras
 import modules.lowvram

 import modules.txt2img

 import modules.img2img

+import modules.sd_models

 

 

 modules.codeformer_model.setup_codeformer()

@@ -33,29 +29,17 @@ shared.face_restorers.append(modules.face_restoration.FaceRestoration())
 esrgan.load_models(cmd_opts.esrgan_models_path)

 realesrgan.setup_realesrgan()

 

+queue_lock = threading.Lock()

 

-def load_model_from_config(config, ckpt, verbose=False):

-    print(f"Loading model [{shared.sd_model_hash}] from {ckpt}")

-    pl_sd = torch.load(ckpt, map_location="cpu")

-    if "global_step" in pl_sd:

-        print(f"Global Step: {pl_sd['global_step']}")

-    sd = pl_sd["state_dict"]

 

-    model = instantiate_from_config(config.model)

-    m, u = model.load_state_dict(sd, strict=False)

-    if len(m) > 0 and verbose:

-        print("missing keys:")

-        print(m)

-    if len(u) > 0 and verbose:

-        print("unexpected keys:")

-        print(u)

-    if cmd_opts.opt_channelslast:

-        model = model.to(memory_format=torch.channels_last)

-    model.eval()

-    return model

+def wrap_queued_call(func):

+    def f(*args, **kwargs):

+        with queue_lock:

+            res = func(*args, **kwargs)

 

+        return res

 

-queue_lock = threading.Lock()

+    return f

 

 

 def wrap_gradio_gpu_call(func):

@@ -80,33 +64,8 @@ def wrap_gradio_gpu_call(func):
 

 modules.scripts.load_scripts(os.path.join(script_path, "scripts"))

 

-try:

-    # this silences the annoying "Some weights of the model checkpoint were not used when initializing..." message at start.

-

-    from transformers import logging

-

-    logging.set_verbosity_error()

-except Exception:

-    pass

-

-with open(cmd_opts.ckpt, "rb") as file:

-    import hashlib

-    m = hashlib.sha256()

-

-    file.seek(0x100000)

-    m.update(file.read(0x10000))

-    shared.sd_model_hash = m.hexdigest()[0:8]

-

-sd_config = OmegaConf.load(cmd_opts.config)

-shared.sd_model = load_model_from_config(sd_config, cmd_opts.ckpt)

-shared.sd_model = (shared.sd_model if cmd_opts.no_half else shared.sd_model.half())

-

-if cmd_opts.lowvram or cmd_opts.medvram:

-    modules.lowvram.setup_for_low_vram(shared.sd_model, cmd_opts.medvram)

-else:

-    shared.sd_model = shared.sd_model.to(shared.device)

-

-modules.sd_hijack.model_hijack.hijack(shared.sd_model)

+shared.sd_model = modules.sd_models.load_model()

+shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights(shared.sd_model)))

 

 

 def webui():