The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Fix regression with clip vision.
comfyanonymous50614f1b7933
diff --git a/comfy/clip_vision.py b/comfy/clip_vision.pyindex 25baf5ca8..87d32a66e 100644--- a/comfy/clip_vision.py+++ b/comfy/clip_vision.py@@ -36,7 +36,8 @@ def clip_preprocess(image, size=224, mean=[0.48145466, 0.4578275, 0.40821073], sreturn (image - mean.view([3,1,1])) / std.view([3,1,1])IMAGE_ENCODERS = {- "clip_vision": comfy.clip_model.CLIPVisionModelProjection,+ "clip_vision_model": comfy.clip_model.CLIPVisionModelProjection,+ "siglip_vision_model": comfy.clip_model.CLIPVisionModelProjection,"dinov2": comfy.image_encoders.dino2.Dinov2Model,}@@ -48,7 +49,7 @@ 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_class = IMAGE_ENCODERS.get(config.get("model_type", "clip_vision_model"))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)