Model reference · open weights
WorldCrafter-Fast is an open-weight video model from TencentARC. WorldCrafter-Fast (BF16) weighs 145 GB; the smallest configuration that runs it is H100 80 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the TencentARC/WorldCrafter-Fast model card, 2026-10-01
What it is
| Released by | TencentARC |
|---|---|
| Released | 2026-09-21 |
| VRAM | 145 GB for the weights |
What it runs on
| Card | Weights | Memory |
|---|---|---|
| RTX 3060 12 GB … L40S 48 GB | does not fit | |
| A100 80 GB | fits (encoders offloaded) | 78.2 GB |
| H100 80 GB | fits (encoders offloaded) | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits (encoders offloaded) | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits (encoders offloaded) | 107 GB |
| H200 141 GB | fits (encoders offloaded) | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
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.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel and load the workflow from the model's card on Hugging Face; choose this model's file in its loader.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the model (10.2 GB)
get TencentARC/WorldCrafter-Fast transformer_high_noise/diffusion_pytorch_model-00006-of-00006.safetensors diffusion_models
get TencentARC/WorldCrafter-Fast text_encoder/model-00005-of-00005.safetensors text_encoders
get TencentARC/WorldCrafter-Fast vae/diffusion_pytorch_model.safetensors vae
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST, PORT and BOOKING are your machine's, from its page in the console
ssh -o HostKeyAlias=axforge-BOOKING -o StrictHostKeyChecking=accept-new -L 8188:localhost:8188 dev@HOST -p PORT