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

Update lora.md to clarify SDXL support (#4503)

* Update lora.md

* Update lora.md
This commit is contained in:
Sayak Paul
2023-08-07 11:06:30 +05:30
committed by GitHub
parent 2e69cf16fe
commit b2456717e6

View File

@@ -401,8 +401,12 @@ Thanks to [@isidentical](https://github.com/isidentical) for helping us on integ
### Known limitations specific to the Kohya-styled LoRAs
* When images don't looks similar to other UIs such ComfyUI, it can be beacause of multiple reasons as explained [here](https://github.com/huggingface/diffusers/pull/4287/#issuecomment-1655110736).
* When images don't looks similar to other UIs, such as ComfyUI, it can be because of multiple reasons, as explained [here](https://github.com/huggingface/diffusers/pull/4287/#issuecomment-1655110736).
* We don't fully support [LyCORIS checkpoints](https://github.com/KohakuBlueleaf/LyCORIS). To the best of our knowledge, our current `load_lora_weights()` should support LyCORIS checkpoints that have LoRA and LoCon modules but not the other ones, such as Hada, LoKR, etc.
## Stable Diffusion XL
We support fine-tuning of the UNet shipped in [Stable Diffusion XL](https://huggingface.co/papers/2307.01952) with DreamBooth and LoRA via the `train_text_to_image_lora_sdxl.py` script. Please refer to the docs [here](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/README_sdxl.md).
We support fine-tuning with [Stable Diffusion XL](https://huggingface.co/papers/2307.01952). Please refer to the following docs:
* [text_to_image/README_sdxl.md](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/README_sdxl.md)
* [dreambooth/README_sdxl.md](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sdxl.md)