AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

fix: minor things in the SDXL docs. (#4070)

Browse Source
This commit is contained in:
Sayak Paul
2023-07-14 09:01:20 +05:30
committed by GitHub
parent f3802eb805
commit 83ca21f539
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_xl.mdx
View File

@@ -85,8 +85,8 @@ faster. The drawback is that one cannot really inspect the output of the base mo
To use the base model and refiner as an ensemble of expert denoisers, make sure to define the fraction
of timesteps which should be run through the high-noise denoising stage (*i.e.* the base model) and the low-noise
denoising stage (*i.e.* the refiner model) respectively. This fraction should be set as the [`~StableDiffusionXLPipeline.__call__.denoising_end`] of the base model
and as the [`~StableDiffusionXLImg2ImgPipeline.__call__.denoising_start`] of the refiner model.
denoising stage (*i.e.* the refiner model) respectively. This fraction should be set as the [`denoising_end`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/stable_diffusion_xl#diffusers.StableDiffusionXLPipeline.__call__.denoising_end) of the base model
and as the [`denoising_start`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/stable_diffusion_xl#diffusers.StableDiffusionXLImg2ImgPipeline.__call__.denoising_start) of the refiner model.
Let's look at an example.
First, we import the two pipelines. Since the text encoders and variational autoencoder are the same
@@ -246,7 +246,7 @@ You can speed up inference by making use of `torch.compile`. This should give yo
+ refiner.unet = torch.compile(refiner.unet, mode="reduce-overhead", fullgraph=True)
```
### Running with `torch` \< 2.0
### Running with `torch < 2.0`
**Note** that if you want to run Stable Diffusion XL with `torch` < 2.0, please make sure to enable xformers
attention: