# JoePenna/Dreambooth-Stable-Diffusion

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focused on training faces, objects, and styles.

Repository: https://github.com/JoePenna/Dreambooth-Stable-Diffusion
Canonical: https://ross.abutalabs.com/products/joepenna-dreambooth-stable-diffusion
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: ai, txt2img, artificial-intelligence, image-generation, machine-learning, model-training, img2img, latent-diffusion, stable-diffusion
Last push: 2024-01-08T12:23:45+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": 1446, "days_push": 968, "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 3211, forks 525 (observed 2026-08-28T04:07:49.347513+00:00)

## What it is
A Jupyter Notebook-based implementation of Dreambooth fine-tuning for Stable Diffusion, adapted from XavierXiao's repo with tweaks for training faces, objects, and styles. It includes setup guides for cloud GPUs (RunPod, Vast.ai, Colab) and local environments, plus captioning and multi-concept support.

## Use cases
- train stable diffusion on my own face
- fine-tune stable diffusion with dreambooth
- create ai images of a specific person or object
- train a stable diffusion model on a custom style
- run dreambooth training on google colab or runpod
- learn how to debug dreambooth training results

## When to choose
- you want a battle-tested, guide-rich dreambooth setup focused on faces and people
- you need step-by-step instructions for cloud GPU providers or local setups
- you want captioning and multi-concept training support for stable diffusion

## When to avoid
- you need a maintained tool with recent updates for the latest stable diffusion versions
- you want a polished GUI rather than notebooks and command-line configs
- you are training models other than stable diffusion

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, llm-training, image-processing
- domain: artificial-intelligence, machine-learning, image-processing
- platform: python, windows
- tags: stable-diffusion, dreambooth, textual-inversion, fine-tuning, diffusers, txt2img, img2img, latent-diffusion, jupyter-notebook, face-training, gpu, linux, macos

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:49.347513+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 2026-08-30T07:24:43.108293+00:00, confidence not recorded.
  - readme: https://github.com/JoePenna/Dreambooth-Stable-Diffusion (fetched 2026-08-28T04:07:49.347513+00:00, sha cc6486cd331b)
- Data as of 2026-08-30T08:39:29.467469+00:00.