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 GLIGEN example to README.
comfyanonymous31e60adb2802
diff --git a/README.md b/README.mdindex be2cb8ec5..bf16006bf 100644--- a/README.md+++ b/README.md@@ -25,6 +25,7 @@ This ui will let you design and execute advanced stable diffusion pipelines usin- [ControlNet and T2I-Adapter](https://comfyanonymous.github.io/ComfyUI_examples/controlnet/)- [Upscale Models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)](https://comfyanonymous.github.io/ComfyUI_examples/upscale_models/)- [unCLIP Models](https://comfyanonymous.github.io/ComfyUI_examples/unclip/)+- [GLIGEN](https://comfyanonymous.github.io/ComfyUI_examples/gligen/)- Starts up very fast.- Works fully offline: will never download anything.- [Config file](extra_model_paths.yaml.example) to set the search paths for models.diff --git a/nodes.py b/nodes.pyindex 8555f272a..48c3ee9c3 100644--- a/nodes.py+++ b/nodes.py@@ -498,7 +498,7 @@ class GLIGENLoader:RETURN_TYPES = ("GLIGEN",)FUNCTION = "load_gligen"- CATEGORY = "_for_testing/gligen"+ CATEGORY = "loaders"def load_gligen(self, gligen_name):gligen_path = folder_paths.get_full_path("gligen", gligen_name)@@ -520,7 +520,7 @@ class GLIGENTextBoxApply:RETURN_TYPES = ("CONDITIONING",)FUNCTION = "append"- CATEGORY = "_for_testing/gligen"+ CATEGORY = "conditioning/gligen"def append(self, conditioning_to, clip, gligen_textbox_model, text, width, height, x, y):c = []