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.

Add image sizes to clip vision outputs. (#11923)

comfyanonymous7ac999bf3069
diff --git a/comfy/clip_vision.py b/comfy/clip_vision.py
index 66f2a9d9c..b28bf636c 100644
--- a/comfy/clip_vision.py
+++ b/comfy/clip_vision.py
@@ -66,6 +66,7 @@ class ClipVisionModel():
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["image_sizes"] = [pixel_values.shape[1:]] * pixel_values.shape[0]
if self.return_all_hidden_states:
all_hs = out[1].to(comfy.model_management.intermediate_device())
outputs["penultimate_hidden_states"] = all_hs[:, -2]