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 format metadata to CLIP save to make compatible with diffusers safetensors loading (#4233)

Silverf3bc40223a3b
diff --git a/comfy_extras/nodes_model_merging.py b/comfy_extras/nodes_model_merging.py
index b0d149c60..136f9a984 100644
--- a/comfy_extras/nodes_model_merging.py
+++ b/comfy_extras/nodes_model_merging.py
@@ -264,6 +264,7 @@ class CLIPSave:
metadata = {}
if not args.disable_metadata:
+ metadata["format"] = "pt"
metadata["prompt"] = prompt_info
if extra_pnginfo is not None:
for x in extra_pnginfo: