dreamoving/dreamoving-project

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1788 stars · 95 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

DreaMoving is the official implementation of a diffusion-based controllable video generation framework from Alibaba that produces high-quality customized human videos. It generates videos of a target person driven by text prompts and pose guidance.

Use cases

• generate videos of a person dancing from a single image
• create customized human videos with text prompts
• animate a face and identity onto pose sequences
• research diffusion-based video generation
• produce controllable human motion videos

When to choose

• you need identity-preserving human video generation from a reference image
• you want to experiment with pose-guided diffusion video synthesis
• you need a research baseline for controllable human video generation

When to avoid

• you need production-grade, actively maintained video generation tooling
• you lack a GPU or don't want to run heavy diffusion models locally
• you need general-purpose video editing rather than human video synthesis

Facets

library · maturity maintenance

video-processing machine-learning deep-learning image-processing deep-learning computer-vision artificial-intelligence python diffusion-models video-generation human-video controllable-generation text-to-video research-code video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="dreamoving/dreamoving-project")