Doubiiu/ToonCrafter

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

6003 stars · 528 forks observed · 2026-08-28

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

ToonCrafter is a generative model that interpolates two cartoon images into a short animation by leveraging pre-trained image-to-video diffusion priors. Published at SIGGRAPH Asia 2024, it also supports sparse sketch guidance and reference-based sketch colorization.

Use cases

• generate in-between frames between two cartoon drawings
• interpolate anime keyframes into a short video clip
• colorize cartoon sketches using reference images
• guide cartoon animation generation with sparse sketches
• create animation from start and end frames with AI
• cartoon video generation from still images

When to choose

• you need generative interpolation tailored to cartoon/anime styles where classical frame interpolation fails
• you want sketch colorization or sketch-guided cartoon animation from a research-grade model
• you need a published, reproducible model with demo endpoints (Hugging Face, Replicate, Colab)

When to avoid

• you need real-time or production video interpolation at high resolution (outputs are 512x320 and diffusion-based, so slow)
• you work with photorealistic video rather than cartoon/anime content
• you need a polished end-user application rather than a research codebase requiring a GPU

Facets

library · maturity stable

machine-learning deep-learning video-processing image-processing stable-diffusion computer-vision image-processing artificial-intelligence deep-learning python cartoon-interpolation image-to-video diffusion-models animation in-betweening sketch-colorization generative-ai research-code video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Doubiiu/ToonCrafter")