Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Add readme note

space-nuko2b2ea5194e04
diff --git a/README.md b/README.md
index bfa8904df..6e0803ab7 100644
--- a/README.md
+++ b/README.md
@@ -29,6 +29,7 @@ This ui will let you design and execute advanced stable diffusion pipelines usin
- [Upscale Models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)](https://comfyanonymous.github.io/ComfyUI_examples/upscale_models/)
- [unCLIP Models](https://comfyanonymous.github.io/ComfyUI_examples/unclip/)
- [GLIGEN](https://comfyanonymous.github.io/ComfyUI_examples/gligen/)
+- Latent previews with [TAESD](https://github.com/madebyollin/taesd)
- Starts up very fast.
- Works fully offline: will never download anything.
- [Config file](extra_model_paths.yaml.example) to set the search paths for models.
@@ -181,6 +182,10 @@ You can set this command line setting to disable the upcasting to fp32 in some c
```--dont-upcast-attention```
+## How to show high-quality previews?
+
+The default installation includes a fast latent preview method that's low-resolution. To enable higher-quality previews with [TAESD](https://github.com/madebyollin/taesd), download the [taesd_encoder.pth](https://github.com/madebyollin/taesd/raw/main/taesd_encoder.pth) and [taesd_decoder.pth](https://github.com/madebyollin/taesd/raw/main/taesd_decoder.pth) models and place them in the `models/taesd` folder. Once they're installed, restart ComfyUI to enable high-quality previews.
+
## Support and dev channel
[Matrix space: #comfyui_space:matrix.org](https://app.element.io/#/room/%23comfyui_space%3Amatrix.org) (it's like discord but open source).