# bytedance/DreamO

[SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization

Repository: https://github.com/bytedance/DreamO
Canonical: https://ross.abutalabs.com/products/dreamo
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-08-14T11:46:35+00:00

## Health v2 (maintenance only)
Score: 35/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 36, release rhythm 35, longevity 35
- inputs: {"age_days": 499, "days_push": 384, "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 1649, forks 136 (observed 2026-08-28T04:05:16.769621+00:00)

## What it is
DreamO is the official PyTorch implementation of a unified framework for image customization, built on FLUX diffusion models. It supports tasks like subject-driven and identity-preserving image generation, with a Gradio demo, quantization support, and consumer-GPU compatibility.

## Use cases
- generate customized images from reference subjects
- identity-preserving portrait generation
- run image customization models on consumer GPUs
- quantize a diffusion model for faster inference
- try a unified image customization demo locally
- integrate image customization into ComfyUI workflows

## When to choose
- you need subject-driven or identity-preserving image generation with a FLUX-based model
- you want a research-backed unified image customization framework with a ready demo
- you need to run image customization on 16-24GB consumer GPUs via quantization and offloading

## When to avoid
- you need a lightweight CPU-only image editing tool
- you want a production image-generation service rather than a research codebase
- you need training/fine-tuning pipelines rather than inference

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, artificial-intelligence, machine-learning
- platform: python, cross-platform
- tags: image-customization, diffusion, flux, text-to-image, gradio, siggraph-asia-2025, subject-driven-generation, model-quantization, gpu

## Member repositories
- bytedance/DreamO (main) score 35

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:16.769621+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 2026-08-30T03:45:07.860657+00:00, confidence not recorded.
  - readme: https://github.com/bytedance/DreamO (fetched 2026-08-28T04:05:16.769621+00:00, sha ebed7110862b)
- Data as of 2026-08-30T08:39:29.467469+00:00.