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

[Doc] update sdxl-controlnet repo name (#4564)

Browse Source 
* rename

* style

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
This commit is contained in:
YiYi Xu
2023-08-10 06:32:32 -10:00
committed by GitHub
parent c697c5ab57
commit 3df52ba8dc
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/api/pipelines/controlnet_sdxl.md
View File

@@ -22,7 +22,7 @@ The abstract from the paper is:
We provide support using ControlNets with [Stable Diffusion XL](./stable_diffusion/stable_diffusion_xl.md) (SDXL).
There are not many ControlNet checkpoints that are compatible with SDXL at the moment. So, we trained one using Canny edge maps as the conditioning images. To know more, check out the [model card](https://huggingface.co/diffusers/controlnet-sdxl-1.0). We encourage you to train custom ControlNets; we provide a [training script](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md) for this.
There are not many ControlNet checkpoints that are compatible with SDXL at the moment. So, we trained one using Canny edge maps as the conditioning images. To know more, check out the [model card](https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0). We encourage you to train custom ControlNets; we provide a [training script](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md) for this.
You can find some results below:

4
src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py
View File

@@ -77,7 +77,9 @@ EXAMPLE_DOC_STRING = """
>>> # initialize the models and pipeline
>>> controlnet_conditioning_scale = 0.5 # recommended for good generalization
>>> controlnet = ControlNetModel.from_pretrained("diffusers/controlnet-sdxl-1.0", torch_dtype=torch.float16)
>>> controlnet = ControlNetModel.from_pretrained(
... "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float16
... )
>>> vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
>>> pipe = StableDiffusionControlNetPipeline.from_pretrained(
... "stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet, torch_dtype=torch.float16