298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-01-25 15:55:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

CLIPVisionEncode can now encode multiple images.

Browse Source
This commit is contained in:
comfyanonymous 2023-08-14 16:54:05 -04:00
parent 0cb6dac943
commit 9cc12c833d
3 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
comfy/clip_vision.py
View File

@ -24,8 +24,8 @@ class ClipVisionModel():
return self.model.load_state_dict(sd, strict=False) return self.model.load_state_dict(sd, strict=False)
def encode_image(self, image): 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) outputs = self.model(**inputs)
return outputs return outputs

18
comfy/model_base.py
View File

@ -120,15 +120,15 @@ class SD21UNCLIP(BaseModel):
weights = [] weights = []
noise_aug = [] noise_aug = []
for unclip_cond in unclip_conditioning: 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: if len(noise_aug) > 1:
adm_out = torch.stack(adm_inputs).sum(0) adm_out = torch.stack(adm_inputs).sum(0)

2
nodes.py
View File

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