Model reference · open weights
VerseCrafter is an open-weight video model from TencentARC. VerseCrafter (BF16) weighs 34.7 GB; the smallest configuration that runs it is L40S 48 GB.
Summary of the TencentARC/VerseCrafter model card, 2026-10-01
What it is
| Released by | TencentARC |
|---|---|
| Released | 2025-12-08 |
| Parameters | 17.3B |
| VRAM | 34.7 GB for the weights |
What it runs on
| Card | Weights | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 5090 32 GB | does not fit | |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control
✨ A controllable video world model with explicit 4D geometric control over camera and multi-object motion.
| Property | Value |
|---|---|
| Base Model | Wan2.1-T2V-14B |
| Resolution | 720 × 1280 |
| Frames | 81 frames |
| Control Signals | Camera trajectory + 3D Gaussian object trajectories |
| Architecture | Frozen DiT + Trainable GeoAdapter |
For installation, inference, and the complete pipeline (depth estimation, segmentation, 3D Gaussian fitting, trajectory customization in Blender, and video generation), please refer to our GitHub repository.
If you find this work useful, please consider citing:
@article{zheng2026versecrafter,
title={VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control},
author={Zheng, Sixiao and Yin, Minghao and Hu, Wenbo and Li, Xiaoyu and Shan, Ying and Fu, Yanwei},
journal={arXiv preprint arXiv:2601.05138},
year={2026}
}
Our work is built upon MoGe, Grounded-SAM-2, VideoX-Fun, Wan2.1 and diffusers.
This project is released under the VerseCrafter License. It is intended for academic/research purposes only and commercial use is not permitted.
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 (8.1 GB)
get TencentARC/VerseCrafter diffusion_pytorch_model-00003-of-00004.safetensors diffusion_models
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST and PORT are your machine's, from its page in the console
ssh -L 8188:localhost:8188 dev@HOST -p PORT