# google/dreambooth

Repository: https://github.com/google/dreambooth
Canonical: https://ross.abutalabs.com/products/dreambooth
License: CC-BY-4.0
License Family: other
Archived: true
Last push: 2023-03-06T21:57:36+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 91
- inputs: {"age_days": 1281, "days_push": 1276, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1029, forks 97 (observed 2026-08-28T04:03:17.654666+00:00)

## What it is
The official dataset accompanying the Google DreamBooth paper on fine-tuning text-to-image diffusion models for subject-driven generation. It contains 4-6 images each for 30 subjects (9 live animals, 21 objects) captured across varied conditions, plus prompts and class names used in the paper.

## Use cases
- evaluate subject-driven image generation models
- fine-tune text-to-image diffusion models on a small set of subject photos
- benchmark personalization methods for generative image models
- research few-shot image generation of specific subjects
- compare novel view synthesis of objects and pets
- reproduce DreamBooth paper experiments

## When to choose
- you need a standard benchmark for subject-driven generation research
- you want to reproduce or compare against the DreamBooth paper
- you need small multi-view image sets of known subjects with prompts and licenses

## When to avoid
- you need large-scale training data for training diffusion models from scratch
- you need a software implementation of DreamBooth rather than the dataset
- you need commercially unrestricted imagery beyond the CC-BY-4.0 and Unsplash licenses

## Facets
- artifact type: dataset
- maturity: stable
- function: machine-learning, image-processing
- domain: machine-learning, image-processing, computer-vision
- platform: cross-platform
- tags: dreambooth, diffusion-models, text-to-image, subject-driven-generation, fine-tuning, research-dataset

## Member repositories
- google/dreambooth (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:17.654666+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 2026-08-30T07:07:39.267613+00:00, confidence not recorded.
  - readme: https://github.com/google/dreambooth (fetched 2026-08-28T04:03:17.654666+00:00, sha 05ea8a0215a9)
- Data as of 2026-08-30T08:39:29.467469+00:00.