mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-09-15 05:57:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

USO style reference. (#9677)

Browse Source 
Load the projector.safetensors file with the ModelPatchLoader node and use
the siglip_vision_patch14_384.safetensors "clip vision" model and the
USOStyleReferenceNode.
This commit is contained in:
comfyanonymous
2025-09-02 12:36:22 -07:00
committed by GitHub
parent e2d1e5dad9
commit 3412d53b1d
5 changed files with 222 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
comfy/clip_vision.py
View File

@@ -50,7 +50,13 @@ class ClipVisionModel():
self.image_size = config.get("image_size", 224)
self.image_mean = config.get("image_mean", [0.48145466, 0.4578275, 0.40821073])
self.image_std = config.get("image_std", [0.26862954, 0.26130258, 0.27577711])
model_class = IMAGE_ENCODERS.get(config.get("model_type", "clip_vision_model"))
model_type = config.get("model_type", "clip_vision_model")
model_class = IMAGE_ENCODERS.get(model_type)
if model_type == "siglip_vision_model":
self.return_all_hidden_states = True
else:
self.return_all_hidden_states = False
self.load_device = comfy.model_management.text_encoder_device()
offload_device = comfy.model_management.text_encoder_offload_device()
self.dtype = comfy.model_management.text_encoder_dtype(self.load_device)
@@ -68,12 +74,18 @@ class ClipVisionModel():
def encode_image(self, image, crop=True):
comfy.model_management.load_model_gpu(self.patcher)
pixel_values = clip_preprocess(image.to(self.load_device), size=self.image_size, mean=self.image_mean, std=self.image_std, crop=crop).float()
out = self.model(pixel_values=pixel_values, intermediate_output=-2)
out = self.model(pixel_values=pixel_values, intermediate_output='all' if self.return_all_hidden_states else -2)
outputs = Output()
outputs["last_hidden_state"] = out[0].to(comfy.model_management.intermediate_device())
outputs["image_embeds"] = out[2].to(comfy.model_management.intermediate_device())
outputs["penultimate_hidden_states"] = out[1].to(comfy.model_management.intermediate_device())
if self.return_all_hidden_states:
all_hs = out[1].to(comfy.model_management.intermediate_device())
outputs["penultimate_hidden_states"] = all_hs[:, -2]
outputs["all_hidden_states"] = all_hs
else:
outputs["penultimate_hidden_states"] = out[1].to(comfy.model_management.intermediate_device())
outputs["mm_projected"] = out[3]
return outputs