nodes/smthemex-ComfyUI_PhotoDoodle
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
smthemex
2025-03-17 13:57:41 +08:00
committed by GitHub
parent aa17a47ae2
commit 14eab62c9f
1 changed files with 11 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+11 -8
View File
@@ -1,6 +1,9 @@
# PhotoDoodle
[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
# Update
* if use repo default use nf4 ,fast,and only 12G VRAM ,and not use mmgp,repo模式默认开启nf4量化，得益于新版的diffuser ，可以在不开启mmgp的情况下，轻松使用
# 1.Installation
-----
In the ./ComfyUI /custom_node directory, run the following:
@@ -12,14 +15,14 @@ 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 OOM try pip install mmgp ，如果OOM ,试一下用mmgp
# 3.checkpoints
* 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
* 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 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
| ├── flux1-dev-fp8.safetensors # if use fp8 single 16G comfy官方单体fp8模型或者flux官方单体模型，正常12G能跑，不用开mmgp
```
* 3.2 more lora download from [here](https://huggingface.co/nicolaus-huang/PhotoDoodle/tree/main)
```
@@ -29,12 +32,12 @@ pip install -r requirements.txt
```
# 4 Example
* if use single files，vae must choice "none" #flux1-dev-fp8.safetensors 16G 单体16G模型，内置clip和vae那种，vae必须选择"none"
* if use single files，vae must choice "none" #flux1-dev-fp8.safetensors 16G 单体16G模型，内置clip和vae那种，vae必须选择"none"，不开启mmgp，次要推荐使用
![](https://github.com/smthemex/ComfyUI_PhotoDoodle/blob/main/assets/example.png)
* if use unet #11G 单体unet模型，没有内置clip和vae的，所以必须要连双clip和选vae
![](https://github.com/smthemex/ComfyUI_PhotoDoodle/blob/main/assets/example_c.png)
* if use repo 'black-forest-labs/FLUX.1-dev' or C:/youpath/black-forest-labs/FLUX.1-dev 如果使用repo可以用自动下载或本地
![](https://github.com/smthemex/ComfyUI_PhotoDoodle/blob/main/assets/example_b.png)
* if use repo 'black-forest-labs/FLUX.1-dev' or C:/youpath/black-forest-labs/FLUX.1-dev 如果使用repo可以用自动下载或本地,不开启mmgp，第一推荐使用
![](https://github.com/smthemex/ComfyUI_PhotoDoodle/blob/main/assets/example_0317.png)
* if use unet #11G 单体unet模型，没有内置clip和vae的，所以必须要连双clip和选vae，可以不开启mmgp，12G可能会OOM
![](https://github.com/smthemex/ComfyUI_PhotoDoodle/blob/main/assets/example_0317A.png)
# 5. Acknowledgments