# open-mmlab/mmagic

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

Repository: https://github.com/open-mmlab/mmagic
Canonical: https://ross.abutalabs.com/products/mmagic
Homepage: https://mmagic.readthedocs.io/en/latest/
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: super-resolution, inpainting, matting, image-generation, generative-adversarial-network, pytorch, deep-learning, video-interpolation, video-frame-interpolation, video-super-resolution, computer-vision, image-editing, image-processing, image-synthesis, diffusion, text2image, aigc, generative-ai, diffusion-models
Last push: 2024-08-06T07:19:40+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2567, "days_push": 757, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7457, forks 1099 (observed 2026-08-28T04:09:59.990387+00:00)

## What it is
MMagic is OpenMMLab's toolbox for generative and multimodal AI image/video creation, built on PyTorch. It provides a large model zoo covering diffusion models, GANs, super-resolution, inpainting, matting, and video frame interpolation with easy-to-use APIs.

## Use cases
- generate images from text prompts with diffusion models
- upscale and restore low-resolution images or videos
- inpaint missing or unwanted regions in photos
- extract foreground mattes from images
- interpolate frames to increase video frame rate
- edit or synthesize images with GANs

## When to choose
- you need a broad PyTorch model zoo for image generation and restoration
- you want pretrained models for super-resolution, inpainting, or matting
- you prefer OpenMMLab-style config-driven training and inference

## When to avoid
- you need the latest actively developed diffusion tooling, as releases have slowed
- you want a lightweight production inference service rather than a research toolbox
- you work outside PyTorch or need non-CV generative tasks like audio or text

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning, video-processing
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python, windows
- tags: generative-ai, diffusion-models, gan, text-to-image, super-resolution, inpainting, matting, video-interpolation, aigc, pytorch, openmmlab, gpu, linux, macos

## Member repositories
- open-mmlab/mmagic (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:59.990387+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 2026-08-29T17:37:39.433449+00:00, confidence not recorded.
  - readme: https://github.com/open-mmlab/mmagic (fetched 2026-08-28T04:09:59.990387+00:00, sha 6b4ce42ff055)
  - registry_pypi: https://pypi.org/pypi/mmagic/json (fetched 2026-08-29T08:33:38.876123+00:00, sha e2877f730bf2)
- Data as of 2026-08-30T08:39:29.467469+00:00.