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 clip vision issue with old transformers versions.
comfyanonymous58f0c616ed16
diff --git a/comfy/clip_vision.py b/comfy/clip_vision.pyindex c408a732d..2c8603bbe 100644--- a/comfy/clip_vision.py+++ b/comfy/clip_vision.py@@ -25,8 +25,7 @@ class ClipVisionModel():def encode_image(self, image):img = torch.clip((255. * image), 0, 255).round().int()- if len(img.shape) == 3:- img = [img]+ img = list(map(lambda a: a, img))inputs = self.processor(images=img, return_tensors="pt")outputs = self.model(**inputs)return outputs