HumanGif: Single-View Human Diffusion with Generative Prior
Paper • 2502.12080 • Published • 1
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Sony/humangif", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]HumanGif Model Card
HumanGif models are the official checkpoints for ther paper "HumanGif: Single-View Human Diffusion with Generative Prior". HumanGif can generate novel view and novel pose human images from a single input conditioned on human poses and camera poses. In this repository, we offer the codes for inference of the model. For detailed information, please refer to the paper.
Model Details
- Finetuned from model: Stable Diffusion v1-5
- SMPL/SMPLX: SMPL/SMPLX
- License: Creative Commons Attribution-NonCommercial 4.0 International (CC-BY-NC 4.0) and CreativeML Open RAIL-M for Use Restrictions. See LICENSE for more details.
Dataset Details
Uses
Direct Use
The model is intended for research purposes only. Possible research areas and tasks include
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
- Generation of artworks and use in design and other artistic processes.
- Research on generative models.
Excluded uses are described below.
Misuse, Malicious Use, and Out-of-Scope Use
Note: This section is taken from the CreativeML Open RAIL-M HumanGif models.
Use Restrictions
You agree not to use the Model or Derivatives of the Model:
- In any way that violates any applicable national, federal, state, local or international law or regulation;
- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
- To generate or disseminate verifiably false information and/or content with the purpose of harming others;
- To generate or disseminate personal identifiable information that can be used to harm an individual;
- To defame, disparage or otherwise harass others;
- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
- To provide medical advice and medical results interpretation;
- To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
Citation
@article{hu2025humangif,
title={HumanGif: Single-View Human Diffusion with Generative Prior},
author={Hu, Shoukang and Narihira, Takuya and Fukuda, Kazumi and Sawata, Ryosuke and Shibuya, Takashi and Mitsufuji, Yuki},
journal={arXiv preprint arXiv:2502.12080},
year={2025}
}
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support