wehub-resource-sync
41 lines
1.4 KiB
Markdown
41 lines
1.4 KiB
Markdown
## 🖌️ Sana-ComfyUI
|
|
|
|
[Original Repo](https://github.com/city96/ComfyUI_ExtraModels)
|
|
|
|
### Model info / implementation
|
|
|
|
- Uses Gemma2 2B as the text encoder
|
|
- Multiple resolutions and models available
|
|
- Compressed latent space (32 channels, /32 compression) - needs custom VAE
|
|
|
|
### Usage
|
|
|
|
1. All the checkpoints will be downloaded automatically.
|
|
1. KSampler(Flow Euler) is available for now; Flow DPM-Solver will be available soon.
|
|
|
|
```bash
|
|
git clone https://github.com/comfyanonymous/ComfyUI.git
|
|
cd ComfyUI
|
|
git clone https://github.com/lawrence-cj/ComfyUI_ExtraModels.git custom_nodes/ComfyUI_ExtraModels
|
|
|
|
python main.py
|
|
```
|
|
|
|
### A sample workflow for Sana
|
|
|
|
[Sana workflow](Sana_FlowEuler.json)
|
|
|
|
|
|
|
|
### A sample for T2I(Sana) + I2V(CogVideoX)
|
|
|
|
[Sana + CogVideoX workflow](Sana_CogVideoX.json)
|
|
|
|
[](https://huggingface.co/datasets/Efficient-Large-Model/Sana-assets/resolve/main/asset/content/comfyui/Sana_CogVideoX_Fun.mp4)
|
|
|
|
### A sample workflow for Sana 4096x4096 image (18GB GPU is needed)
|
|
|
|
[Sana workflow](Sana_FlowEuler_4K.json)
|
|
|
|
|