guoyww/AnimateDiff

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

12227 stars · 1093 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Official implementation of AnimateDiff, a plug-and-play motion modeling module that turns personalized text-to-image diffusion models (e.g., Stable Diffusion) into animation generators without additional per-model training. It provides training and inference code, with official support in Hugging Face Diffusers.

Use cases

• generate animated gifs from text prompts with stable diffusion
• animate personalized text-to-image models like LoRA checkpoints
• add motion to community SD1.5 models without retraining
• train a motion module on video clips
• create text-driven animation videos from custom models

When to choose

• you want to animate existing Stable Diffusion v1.5 or SDXL checkpoints
• you need a research-grade implementation of the AnimateDiff paper
• you want plug-and-play motion modules usable with Diffusers

When to avoid

• you need production video generation at scale
• you want a polished end-user GUI rather than Python scripts
• you need models beyond the Stable Diffusion family

Facets

library · maturity active

machine-learning deep-learning video-processing image-processing stable-diffusion artificial-intelligence deep-learning image-processing graphics python cross-platform text-to-video diffusion-models animation-generator motion-module stable-diffusion iclr-2024 plug-and-play video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="guoyww/AnimateDiff")