introduce minimalistic reimplementation of SDXL on the SDXL doc (#4532)

minsdxl

introduce minimalistic reimplementation of SDXL on the SDXL doc (#4532)
minsdxl
e7e37494 · Simo Ryu · GitHub · c7c0b575 · e7e37494
Unverified Commit e7e37494 authored Aug 09, 2023 by Simo Ryu Committed by GitHub Aug 09, 2023
Hide whitespace changes
Inline Side-by-side

Showing with 4 additions and 0 deletions

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_xl.md .../en/api/pipelines/stable_diffusion/stable_diffusion_xl.md +4 -0

No files found.
--- a/docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_xl.md
+++ b/docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_xl.md
@@ -425,3 +425,7 @@ prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
 prompt_2 = "monet painting"
 image = pipe(prompt=prompt, prompt_2=prompt_2).images[0]
 ```
+
+## Single-file Implementation of SDXL Unet Model
+
+If you are curious about how SDXL Unet is implemented and would like to make quick modifications / experimentations, you can alternatively head to [`minSDXL`](https://github.com/cloneofsimo/minSDXL) that is very `diffusers` friendly. It is a single-file implementation of SDXL Unet model that is written in PyTorch with exact same model naming and structure as in `diffusers`.
\ No newline at end of file