woctordho commited on
Commit
da551c7
·
verified ·
1 Parent(s): 2668fb8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  See https://huggingface.co/woctordho/sdxl-control-lora for an introduction of this.
2
 
3
- Black Forest Labs' LoRAs are taken from [FLUX.1-Canny-dev-lora](https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev-lora) and [FLUX.1-Depth-dev-lora](https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev-lora), and pruned using [resize_lora.py](https://github.com/kohya-ss/sd-scripts/blob/main/networks/resize_lora.py) in Kohya's sd-scripts. They're in a different format from SDXL ControlLoRAs, so they should be loaded in `LoraLoaderModelOnly` node and used in `InstructPixToPixConditioning` node, see https://docs.comfy.org/tutorials/flux/flux-1-controlnet#flux-1-depth-dev-lora-workflow
4
 
5
  Sometimes Shakker Labs' union ControlNet can follow the control better than Black Forest Labs' models, but it's in another different format and I need more time to figure out how to prune and load it.
 
1
  See https://huggingface.co/woctordho/sdxl-control-lora for an introduction of this.
2
 
3
+ Black Forest Labs' LoRAs are taken from [FLUX.1-Canny-dev-lora](https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev-lora) and [FLUX.1-Depth-dev-lora](https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev-lora), and pruned using [resize_lora.py](https://github.com/kohya-ss/sd-scripts/blob/main/networks/resize_lora.py) in Kohya's sd-scripts. They're in a different format from SDXL ControlLoRAs, so they should be loaded in `LoraLoaderModelOnly` node and used in `InstructPixToPixConditioning` node, see the [example workflow](https://docs.comfy.org/tutorials/flux/flux-1-controlnet#flux-1-depth-dev-lora-workflow).
4
 
5
  Sometimes Shakker Labs' union ControlNet can follow the control better than Black Forest Labs' models, but it's in another different format and I need more time to figure out how to prune and load it.