metadata
license: apache-2.0
pipeline_tag: image-classification
Venus-DefakerOne2: A Vision-Forensics Foundation Model
with Broader Coverage
GuangJian Team, Ant Group
Technical Committee on Digital Media Forensics and Security, CSIG
1. Environment Requirements
Python 3.12.3
pip install torch==2.9.0 torchvision==0.24.0 ms-swift=4.1.0 numpy==1.26.0 scipy==1.11.3 scikit-learn==1.3.2 torchao==0.16.0
2. Model Download
modelscope download --model DanceText/DefakerOne2 --local_dir [target_save_path]
Two checkpoints are provided under the download directory:
| Directory | Description |
|---|---|
preview/ |
DefakerOne2-preview — can be used for reproducing the scores reported in the paper. |
release/ |
DefakerOne2-release — trained with more data; expected to perform better in most cases. |
3. Inference Data Format
Inference inputs are JSONL files, one sample per line.
Image
{"messages": [{"role": "user", "content": "<image>Is this image real or fake? Answer only Real or Fake"}], "images": ["your_image_path.jpg"]}
Video
{"messages": [{"role": "user", "content": "<video>Is this video real or fake? Answer only Real or Fake"}], "images": ["your_video_path.mp4"]}
The prompt is fixed and direct, so the model commits to its conclusion in a single output token (Real / Fake).
4. Inference Command
CUDA_VISIBLE_DEVICES=0 MIN_PIXELS=262144 MAX_PIXELS=2408448 --model [model_weight_dir] --val_dataset [val_dataset_jsonl_path] --result_path [prediction_jsonl_save_path] --max_new_token 16 --enable_thinking False --batch_size 1 --num_workers 8 --logprobs True --top_logprobs 20
5. Citation
@misc{qu2026venusdefakerone2visionforensicsfoundationmodel,
title={Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage},
author={Chenfan Qu and Yachao Liang and Mingqi Fang and Jiangwei Xie and Zhenming Wang and Baoyue Zhang and Changjiang Jiang and Zheng Chang and Fanli Jin and Xuekang Zhu and Kaiwen Feng and Junchi Li and Weihong Zhang and Haoyue Wang and Chenfeng Zhang and Yinan Xia and Fangming Cui and Dong Fan and Jingjing Liu and Tianyi Zhang and Luobin Chen and Ji-Zhe Zhou and Sheng Li and Wei Wang and Bin Li and Ran He and Xinpeng Zhang and Linna Zhou and Jian Liu and Weiqiang Wang},
year={2026},
eprint={2610.37918},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2610.37918},
}