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

1 files changed, 30 insertions, 36 deletions

diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py
index 5c0488e5..631a08ef 100644
--- a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py
+++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py
@@ -48,7 +48,7 @@ class DDPMV1(pl.LightningModule):
                  beta_schedule="linear",
                  loss_type="l2",
                  ckpt_path=None,
-                 ignore_keys=[],
+                 ignore_keys=None,
                  load_only_unet=False,
                  monitor="val/loss",
                  use_ema=True,
@@ -100,7 +100,7 @@ class DDPMV1(pl.LightningModule):
         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.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [], 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)
@@ -182,13 +182,13 @@ class DDPMV1(pl.LightningModule):
                 if context is not None:
                     print(f"{context}: Restored training weights")
 
-    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+    def init_from_ckpt(self, path, ignore_keys=None, 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:
+            for ik in ignore_keys or []:
                 if k.startswith(ik):
                     print("Deleting key {} from state_dict.".format(k))
                     del sd[k]
@@ -375,7 +375,7 @@ class DDPMV1(pl.LightningModule):
 
     @torch.no_grad()
     def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
-        log = dict()
+        log = {}
         x = self.get_input(batch, self.first_stage_key)
         N = min(x.shape[0], N)
         n_row = min(x.shape[0], n_row)
@@ -383,7 +383,7 @@ class DDPMV1(pl.LightningModule):
         log["inputs"] = x
 
         # get diffusion row
-        diffusion_row = list()
+        diffusion_row = []
         x_start = x[:n_row]
 
         for t in range(self.num_timesteps):
@@ -444,13 +444,13 @@ class LatentDiffusionV1(DDPMV1):
             conditioning_key = None
         ckpt_path = kwargs.pop("ckpt_path", None)
         ignore_keys = kwargs.pop("ignore_keys", [])
-        super().__init__(conditioning_key=conditioning_key, *args, **kwargs)
+        super().__init__(*args, conditioning_key=conditioning_key, **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:
+        except Exception:
             self.num_downs = 0
         if not scale_by_std:
             self.scale_factor = scale_factor
@@ -460,7 +460,7 @@ class LatentDiffusionV1(DDPMV1):
         self.instantiate_cond_stage(cond_stage_config)
         self.cond_stage_forward = cond_stage_forward
         self.clip_denoised = False
-        self.bbox_tokenizer = None  
+        self.bbox_tokenizer = None
 
         self.restarted_from_ckpt = False
         if ckpt_path is not None:
@@ -792,7 +792,7 @@ class LatentDiffusionV1(DDPMV1):
                 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):  
+                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])]
@@ -877,16 +877,6 @@ class LatentDiffusionV1(DDPMV1):
                 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):
@@ -900,7 +890,7 @@ class LatentDiffusionV1(DDPMV1):
 
         if hasattr(self, "split_input_params"):
             assert len(cond) == 1  # todo can only deal with one conditioning atm
-            assert not return_ids  
+            assert not return_ids
             ks = self.split_input_params["ks"]  # eg. (128, 128)
             stride = self.split_input_params["stride"]  # eg. (64, 64)
 
@@ -1126,7 +1116,7 @@ class LatentDiffusionV1(DDPMV1):
         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}
+                [x[:batch_size] for x in cond[key]] for key in cond}
             else:
                 cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
 
@@ -1157,8 +1147,10 @@ class LatentDiffusionV1(DDPMV1):
 
             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)
+            if callback:
+                callback(i)
+            if img_callback:
+                img_callback(img, i)
         return img, intermediates
 
     @torch.no_grad()
@@ -1205,8 +1197,10 @@ class LatentDiffusionV1(DDPMV1):
 
             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 callback:
+                callback(i)
+            if img_callback:
+                img_callback(img, i)
 
         if return_intermediates:
             return img, intermediates
@@ -1221,7 +1215,7 @@ class LatentDiffusionV1(DDPMV1):
         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}
+                [x[:batch_size] for x in 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,
@@ -1253,7 +1247,7 @@ class LatentDiffusionV1(DDPMV1):
 
         use_ddim = ddim_steps is not None
 
-        log = dict()
+        log = {}
         z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
                                            return_first_stage_outputs=True,
                                            force_c_encode=True,
@@ -1280,7 +1274,7 @@ class LatentDiffusionV1(DDPMV1):
 
         if plot_diffusion_rows:
             # get diffusion row
-            diffusion_row = list()
+            diffusion_row = []
             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:
@@ -1322,7 +1316,7 @@ class LatentDiffusionV1(DDPMV1):
 
             if inpaint:
                 # make a simple center square
-                b, h, w = z.shape[0], z.shape[2], z.shape[3]
+                h, w = 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.
@@ -1424,10 +1418,10 @@ 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)
+        super().__init__(*args, cond_stage_key=cond_stage_key, **kwargs)
 
     def log_images(self, batch, N=8, *args, **kwargs):
-        logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+        logs = super().log_images(*args, batch=batch, N=N, **kwargs)
 
         key = 'train' if self.training else 'validation'
         dset = self.trainer.datamodule.datasets[key]
@@ -1443,7 +1437,7 @@ class Layout2ImgDiffusionV1(LatentDiffusionV1):
         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)
+ldm.models.diffusion.ddpm.DDPMV1 = DDPMV1
+ldm.models.diffusion.ddpm.LatentDiffusionV1 = LatentDiffusionV1
+ldm.models.diffusion.ddpm.DiffusionWrapperV1 = DiffusionWrapperV1
+ldm.models.diffusion.ddpm.Layout2ImgDiffusionV1 = Layout2ImgDiffusionV1