# Hugging Face — Training Stable Diffusion with Dreambooth using Diffusers

- Company: Hugging Face (huggingface.co)
- Announced: 2022-11-07
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://huggingface.co/blog/dreambooth
- Record: https://forck.live/items/2137-training-stable-diffusion-with-dreambooth-using-diffusers
- Subject: Platform
- Models affected: Stable Diffusion
- License: CreativeML Open RAIL-M license

Experimental findings and recommendations for fine-tuning Stable Diffusion with Dreambooth using the Diffusers library, including optimal hyperparameters and the importance of prior preservation for faces.

## Evidence

Verbatim from https://huggingface.co/blog/dreambooth:

> We conducted a lot of experiments to analyze the effect of different settings in Dreambooth. This post presents our findings and some tips to improve your results when fine-tuning Stable Diffusion with Dreambooth.

---

Record: https://forck.live/items/2137-training-stable-diffusion-with-dreambooth-using-diffusers
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md