# microsoft/NUWA

A unified 3D Transformer Pipeline for visual synthesis

Repository: https://github.com/microsoft/NUWA
Canonical: https://ross.abutalabs.com/products/microsoft-nuwa
License Family: other
Archived: true
Last push: 2023-05-29T09:07:41+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1764, "days_push": 1192, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2791, forks 163 (observed 2026-08-28T04:07:22.193722+00:00)

## What it is
Microsoft's official research repository for the NUWA family of multimodal generative models, a unified 3D transformer pipeline for visual synthesis. It covers text-to-image and text-to-video generation, image inpainting, infinite-resolution visual synthesis, and extremely long video generation via diffusion.

## Use cases
- generate images from text prompts
- generate videos from text descriptions
- inpaint missing regions in images guided by language
- create arbitrarily large high-resolution images
- generate extremely long videos with diffusion models
- produce 3D photography videos from a single image

## When to choose
- you need research-grade text-to-image or text-to-video generation models
- you want to reproduce or build on published NUWA papers
- you need long-duration or infinite-size visual synthesis experiments

## When to avoid
- you need a production-ready, well-supported image generation product
- you require a permissive license for commercial use (no license is provided)
- you want a simple plug-and-play library rather than research code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, video-processing, nlp
- domain: artificial-intelligence, deep-learning, computer-vision, image-processing
- platform: python
- tags: text-to-image, text-to-video, visual-synthesis, transformer, diffusion, research-code, generative-models, video, gpu

## Member repositories
- microsoft/NUWA (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:22.193722+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 2026-08-30T08:15:16.229066+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/NUWA (fetched 2026-08-28T04:07:22.193722+00:00, sha 82ae31d0c292)
- Data as of 2026-08-30T08:39:29.467469+00:00.