# Doubiiu/DynamiCrafter

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Repository: https://github.com/Doubiiu/DynamiCrafter
Canonical: https://ross.abutalabs.com/products/dynamicrafter
Homepage: https://doubiiu.github.io/projects/DynamiCrafter/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: image-animation, image-to-video, video-generation
Last push: 2024-09-08T23:43:53+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 72
- inputs: {"age_days": 1010, "days_push": 724, "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 3007, forks 243 (observed 2026-08-28T04:07:37.650027+00:00)

## What it is
DynamiCrafter is an open-source research model that animates open-domain still images into short videos using pre-trained video diffusion priors, guided by text prompts. It includes training/fine-tuning code, pretrained weights at multiple resolutions, and generative frame interpolation and looping video capabilities.

## Use cases
- animate a still image into a video with a text prompt
- convert a photo to a short video clip
- generate video from a single image using diffusion models
- do generative frame interpolation between images
- create looping videos from still images
- fine-tune an image-to-video diffusion model
- make AI-generated story shots move

## When to choose
- you need research-grade image-to-video generation with text motion control
- you want to fine-tune or train an image animation model yourself
- you need frame interpolation or looping video generation from stills
- you want a model with strong VBench I2V benchmark performance

## When to avoid
- you need production video editing rather than generative animation
- you lack a GPU or cannot run large diffusion models locally
- you need long-form or high-fidelity commercial video generation
- you want a polished end-user app rather than a research codebase

## Facets
- artifact type: library
- maturity: active
- function: image-processing, video-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, artificial-intelligence, deep-learning
- platform: python
- tags: image-to-video, video-diffusion, diffusion-models, frame-interpolation, text-guided-animation, eccv-2024, generative-ai, video, gpu, linux

## Member repositories
- Doubiiu/DynamiCrafter (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:37.650027+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 2026-08-30T07:30:20.770750+00:00, confidence not recorded.
  - readme: https://github.com/Doubiiu/DynamiCrafter (fetched 2026-08-28T04:07:37.650027+00:00, sha 0d95ff6888a4)
  - homepage: https://doubiiu.github.io/projects/DynamiCrafter/ (fetched 2026-08-29T09:45:36.845966+00:00, sha 137bcfe5442a)
- Data as of 2026-08-30T08:39:29.467469+00:00.