Update README.md

README.md

@@ -16,6 +16,7 @@ For each model below, you'll find:
 - *Rank 128* files (reducing to model down to `~377MB`)
 
 Each Control-LoRA has been trained on a diverse range of image concepts and aspect ratios.
+
 ### MiDaS and ClipDrop Depth
 ![canny](samples/depth-sample.jpeg)
 
@@ -39,10 +40,6 @@ These two Control-LoRAs can be used to colorize images.
 
 *Sketch* is designed to color in drawings input as a white-on-black image (either hand-drawn, or created with a `pidi` edge model).
 
-**ComfyUI example workflow:** ![comfyui recolor](samples/comfyui-recolor-example.jpeg)
-
-**StableSwarmUI example:** ![swarmui recolor](samples/swarmui-recolor-example.jpeg)
-
 ### Revision
 ![revision](thumbnails/stability-clora-revision-thumbnail.jpeg)
 Revision is a novel approach of using images to prompt SDXL.
@@ -51,3 +48,13 @@ It uses pooled CLIP embeddings to produce images conceptually similar to the inp
 
 Revision also includes a blending function for combining multiple image or text concepts, as either positive or negative prompts.
 
+
+## Inference
+
+Control-LoRAs have been implemented into [ComfyUI](https://github.com/comfyanonymous/ComfyUI) and [StableSwarmUI](https://github.com/Stability-AI/StableSwarmUI)
+
+Basic ComfyUI workflows (using the base model only) are available in this repo.
+
+**ComfyUI example Recolor workflow:** ![comfyui recolor](samples/comfyui-recolor-example.jpeg)
+
+**StableSwarmUI Canny example:** ![swarmui recolor](samples/swarmui-canny-example.jpeg)