alihan/SwarmUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

note VAE requirement in GGUF support doc

Browse Source
This commit is contained in:
Alex "mcmonkey" Goodwin
2024-09-22 23:48:50 +09:00
parent ccbb7c3320
commit 5aa5f68c8a
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/Model Support.md
View File

@@ -135,6 +135,8 @@ Download the model, then click "`Edit Metadata`" and select `(Temporary) AuraFlo
- GGUF Quantized `diffusion_models` models, such as Flux Schnell <https://huggingface.co/city96/FLUX.1-schnell-gguf/tree/main> or Flux Dev <https://huggingface.co/city96/FLUX.1-dev-gguf/tree/main> are supported in SwarmUI automatically.
- The detection is based on file extension.
- They go in `(Swarm)/Models/diffusion_models` and work similar to other `diffusion_models` format models
- You will need a relevant VAE in your `(Swarm)/Models/VAE` folder
- For Flux you need <https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/ae.safetensors>
- You will have to click `Edit Metadata` on the model and set the architecture, it cannot be autodetected currently.
- The first time you try to load a GGUF model, it will give you a popup asking to install support
- This will autoinstall https://github.com/city96/ComfyUI-GGUF which is developed by city96.