Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models
Paper • 2507.13344 • Published • 59
Video-to-Video
Diffusers
Safetensors
Diffuman4DPipeline
3d-generation
4d-generation
human
avatar
multi-view video
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("krahets/Diffuman4D", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Diffuman4D Model
Project Page | Paper | Code | Dataset
The official model repo for Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models.
Diffuman4D enables high-fidelity free-viewpoint rendering of human performances from sparse-view videos.
Usage
See the GitHub repo for detailed usage.
Cite
@inproceedings{jin2025diffuman4d,
title={Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models},
author={Jin, Yudong and Peng, Sida and Wang, Xuan and Xie, Tao and Xu, Zhen and Yang, Yifan and Shen, Yujun and Bao, Hujun and Zhou, Xiaowei},
booktitle={International Conference on Computer Vision (ICCV)},
year={2025}
}
- Downloads last month
- 510
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for krahets/Diffuman4D
Base model
stabilityai/stable-diffusion-2-1-base