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 hypernetwork example link to readme.

comfyanonymous463bde66a1d2
diff --git a/README.md b/README.md
index bf16006bf..5b6346a67 100644
--- a/README.md
+++ b/README.md
@@ -17,6 +17,7 @@ This ui will let you design and execute advanced stable diffusion pipelines usin
- Can load ckpt, safetensors and diffusers models/checkpoints. Standalone VAEs and CLIP models.
- Embeddings/Textual inversion
- [Loras (regular, locon and loha)](https://comfyanonymous.github.io/ComfyUI_examples/lora/)
+- [Hypernetworks](https://comfyanonymous.github.io/ComfyUI_examples/hypernetworks/)
- Loading full workflows (with seeds) from generated PNG files.
- Saving/Loading workflows as Json files.
- Nodes interface can be used to create complex workflows like one for [Hires fix](https://comfyanonymous.github.io/ComfyUI_examples/2_pass_txt2img/) or much more advanced ones.
diff --git a/comfy_extras/nodes_hypernetwork.py b/comfy_extras/nodes_hypernetwork.py
index c08c2c811..0c7250e43 100644
--- a/comfy_extras/nodes_hypernetwork.py
+++ b/comfy_extras/nodes_hypernetwork.py
@@ -93,7 +93,7 @@ class HypernetworkLoader:
RETURN_TYPES = ("MODEL",)
FUNCTION = "load_hypernetwork"
- CATEGORY = "_for_testing"
+ CATEGORY = "loaders"
def load_hypernetwork(self, model, hypernetwork_name, strength):
hypernetwork_path = folder_paths.get_full_path("hypernetworks", hypernetwork_name)