WorldCrafter-Fast

Self-contained weights for WorldCrafter Fast image-to-video, text-to-video, and the interactive image-to-video demo. Use the WorldCrafter inference code and its pinned uv environment.

The two transformer branches have independent DMD LoRA and camera adapters. The RepEncoder, text encoder, tokenizer, VAE, and scheduler are included here. No WorldCrafter-Base files are needed for Fast inference.

From the code repository root:

python inference.py --model-type fast --model-path weights/WorldCrafter-Fast --output-path outputs/fast.mp4

Image-to-video uses five high-noise steps and one low-noise step per chunk. Text-to-video uses four high-noise and eight low-noise steps for the first chunk, then two high-noise and four low-noise steps. Compilation is optional with --enable-compile.

inference_config.json resolves shared components from this directory (shared_components: "."). Keep all component folders together. manifest.json records checkpoint provenance and validation hashes; SHA256SUMS covers the packaged files.

Paper and Resources

• Paper: WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
• Project page: https://drexubery.github.io/WorldCrafter
• Code: https://github.com/TencentARC/WorldCrafter