Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

CLIPVisionEncode can now encode multiple images.

comfyanonymous9cc12c833d60
diff --git a/comfy/clip_vision.py b/comfy/clip_vision.py
index e2bc3209d..8d04faf71 100644
--- a/comfy/clip_vision.py
+++ b/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()
- inputs = self.processor(images=[img], return_tensors="pt")
+ img = torch.clip((255. * image), 0, 255).round().int()
+ inputs = self.processor(images=img, return_tensors="pt")
outputs = self.model(**inputs)
return outputs
diff --git a/comfy/model_base.py b/comfy/model_base.py
index bf6983fc2..c3c807a68 100644
--- a/comfy/model_base.py
+++ b/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
- weight = unclip_cond["strength"]
- noise_augment = unclip_cond["noise_augmentation"]
- 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))
- adm_out = torch.cat((c_adm, noise_level_emb), 1) * weight
- weights.append(weight)
- noise_aug.append(noise_augment)
- adm_inputs.append(adm_out)
+ for adm_cond in unclip_cond["clip_vision_output"].image_embeds:
+ weight = unclip_cond["strength"]
+ noise_augment = unclip_cond["noise_augmentation"]
+ 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))
+ adm_out = torch.cat((c_adm, noise_level_emb), 1) * weight
+ weights.append(weight)
+ noise_aug.append(noise_augment)
+ adm_inputs.append(adm_out)
if len(noise_aug) > 1:
adm_out = torch.stack(adm_inputs).sum(0)
diff --git a/nodes.py b/nodes.py
index 92baffe30..5f7ea95c0 100644
--- a/nodes.py
+++ b/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()]