Merge branch 'comfyanonymous:master' into bugfix/extra_data

.github/workflows/windows_release_cu118_dependencies_2.yml

@@ -2,6 +2,13 @@ name: "Windows Release cu118 dependencies 2"
 
 on:
   workflow_dispatch:
+    inputs:
+      xformers:
+        description: 'xformers version'
+        required: true
+        type: string
+        default: "xformers"
+
 #  push:
 #    branches:
 #      - master
@@ -17,7 +24,7 @@ jobs:
 
         - shell: bash
           run: |
-            python -m pip wheel --no-cache-dir torch torchvision torchaudio xformers --extra-index-url https://download.pytorch.org/whl/cu118 -r requirements.txt pygit2 -w ./temp_wheel_dir
+            python -m pip wheel --no-cache-dir torch torchvision torchaudio ${{ inputs.xformers }} --extra-index-url https://download.pytorch.org/whl/cu118 -r requirements.txt pygit2 -w ./temp_wheel_dir
             python -m pip install --no-cache-dir ./temp_wheel_dir/*
             echo installed basic
             ls -lah temp_wheel_dir

CODEOWNERS

@@ -0,0 +1 @@
+*       @comfyanonymous

comfy/clip_vision.py

@@ -24,8 +24,8 @@ class ClipVisionModel():
         return self.model.load_state_dict(sd, strict=False)
 
     def encode_image(self, image):
-        img = torch.clip((255. * image[0]), 0, 255).round().int()
+        img = torch.clip((255. * image), 0, 255).round().int()
-        inputs = self.processor(images=[img], return_tensors="pt")
+        inputs = self.processor(images=img, return_tensors="pt")
         outputs = self.model(**inputs)
         return outputs
 

comfy/model_base.py

@@ -120,15 +120,15 @@ class SD21UNCLIP(BaseModel):
             weights = []
             noise_aug = []
             for unclip_cond in unclip_conditioning:
-                adm_cond = unclip_cond["clip_vision_output"].image_embeds
+                for adm_cond in unclip_cond["clip_vision_output"].image_embeds:
-                weight = unclip_cond["strength"]
+                    weight = unclip_cond["strength"]
-                noise_augment = unclip_cond["noise_augmentation"]
+                    noise_augment = unclip_cond["noise_augmentation"]
-                noise_level = round((self.noise_augmentor.max_noise_level - 1) * noise_augment)
+                    noise_level = round((self.noise_augmentor.max_noise_level - 1) * noise_augment)
-                c_adm, noise_level_emb = self.noise_augmentor(adm_cond.to(device), noise_level=torch.tensor([noise_level], device=device))
+                    c_adm, noise_level_emb = self.noise_augmentor(adm_cond.to(device), noise_level=torch.tensor([noise_level], device=device))
-                adm_out = torch.cat((c_adm, noise_level_emb), 1) * weight
+                    adm_out = torch.cat((c_adm, noise_level_emb), 1) * weight
-                weights.append(weight)
+                    weights.append(weight)
-                noise_aug.append(noise_augment)
+                    noise_aug.append(noise_augment)
-                adm_inputs.append(adm_out)
+                    adm_inputs.append(adm_out)
 
             if len(noise_aug) > 1:
                 adm_out = torch.stack(adm_inputs).sum(0)

nodes.py

@@ -771,7 +771,7 @@ class StyleModelApply:
     CATEGORY = "conditioning/style_model"
 
     def apply_stylemodel(self, clip_vision_output, style_model, conditioning):
-        cond = style_model.get_cond(clip_vision_output)
+        cond = style_model.get_cond(clip_vision_output).flatten(start_dim=0, end_dim=1).unsqueeze(dim=0)
         c = []
         for t in conditioning:
             n = [torch.cat((t[0], cond), dim=1), t[1].copy()]