# XavierXiao/Dreambooth-Stable-Diffusion

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

Repository: https://github.com/XavierXiao/Dreambooth-Stable-Diffusion
Canonical: https://ross.abutalabs.com/products/dreambooth-stable-diffusion
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: pytorch, pytorch-lightning, stable-diffusion, text-to-image
Last push: 2022-12-08T02:19:03+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1457, "days_push": 1365, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7738, forks 795 (observed 2026-08-28T04:10:02.715093+00:00)

## What it is
An implementation of Google's Dreambooth fine-tuning method applied to Stable Diffusion, enabling personalization of a text-to-image diffusion model with a few example images. It is built on top of the Textual Inversion codebase but fine-tunes the entire diffusion model rather than just word embeddings.

## Use cases
- fine-tune stable diffusion on photos of my dog
- personalize a text-to-image model with a few images
- train dreambooth on stable diffusion v1.4
- generate images of a specific subject after fine-tuning
- reduce GPU memory when fine-tuning the UNet with gradient checkpointing

## When to choose
- you want the original minimal Dreambooth implementation for Stable Diffusion v1
- you want to fine-tune the full UNet rather than only embeddings
- you need a research-grade reference implementation based on the Textual Inversion codebase

## When to avoid
- you need actively maintained support for newer Stable Diffusion versions like SDXL
- you want a polished tool with a UI or one-click training
- you need memory-efficient training on consumer GPUs beyond what this codebase offers

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-training, machine-learning, image-processing
- domain: deep-learning, image-processing, artificial-intelligence
- platform: python
- tags: dreambooth, stable-diffusion, fine-tuning, text-to-image, diffusion-models, pytorch-lightning, gpu

## Member repositories
- XavierXiao/Dreambooth-Stable-Diffusion (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:02.715093+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:35:11.124986+00:00, confidence not recorded.
  - readme: https://github.com/XavierXiao/Dreambooth-Stable-Diffusion (fetched 2026-08-28T04:10:02.715093+00:00, sha 299f040810b5)
- Data as of 2026-08-30T08:39:29.467469+00:00.