diff --git a/README.md b/README.md index 878c8b2..67998ae 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,5 @@ # PhotoDoodle -PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data,you can use it in comfyUI +[PhotoDoodle](https://github.com/showlab/PhotoDoodle) it a method about 'Learning Artistic Image Editing from Few-Shot Pairwise Data',you can use it in comfyUI # 1.Installation ----- @@ -12,16 +12,16 @@ git clone https://github.com/smthemex/ComfyUI_PhotoDoodle ``` pip install -r requirements.txt ``` -If Vram <=24G pip install mmgp ,这个方法适配的显存是40G,所以4090及以下显卡都要按照mmpg,这样才能跑得快,4090模型加载菜单,可以选0,或者1或者2 +* If Vram <=24G pip install mmgp ,这个方法适配的显存是40G,所以4090及以下显卡都要按照mmpg,这样才能跑得快,4090模型加载菜单,可以选0,或者1或者2 # 3.checkpoints -* 3 mode use flux dev single checkpoints(fp8 or fp16) or repo or unet+ae+comfyui T5XXX ,三种选择,使用flux dev的fp8或fp16单体模型 或者使用repo,或者使用flux unet+ae+comfy的T5双clip +* 3.1 mode use flux dev single checkpoints(fp8 or fp16) or repo or unet+ae+comfyui T5XXX ,三种选择,使用flux dev的fp8或fp16单体模型 或者使用repo,或者使用flux unet+ae+comfy的T5双clip ``` ├── ComfyUI/models/diffusion_models/ -| ├── flux1-kj-dev-fp8.safetensors # if use fp8 unet 11G 不推荐,因为更容易爆显存 -| ├── flux1-dev-fp8.safetensors # if use fp8 single 16G 推荐 +| ├── flux1-kj-dev-fp8.safetensors # if use fp8 unet 11G unet+vae+clip方法不推荐,因为更容易爆显存 +| ├── flux1-dev-fp8.safetensors # if use fp8 single 16G comfy官方单体模型或者flux官方单体模型,推荐,开启mmgp不会爆显存,虽然慢 ``` -lora download from [here](https://huggingface.co/nicolaus-huang/PhotoDoodle/tree/main) +* 3.2 more lora download from [here](https://huggingface.co/nicolaus-huang/PhotoDoodle/tree/main) ``` ├── ComfyUI/models/loras/ | ├── pretrain.safetensors # 必须要