_{^{Self-Adversarial One Step Generation via Condition Shifting}}

Deyuan Liu^*   ·   Peng Sun^*   ·   Yansen Han   ·   Zhenglin Cheng   ·   Chuyan Chen   ·   Tao Lin

   

Join the WeChat Group, feel free to reach out anytime if you have any questions!👇

👇 WeChat Group QR Code/微信群二维码 👇

• Technical Discussion Group 1 is full, please join Technical Discussion Group 2

Technical Discussion Group/技术讨论群	Model Users Discussion Group/AIGC模型使用讨论群

🧭 Table of Contents

• 🔥 Codebase Usage 🔥

📰 News

• We release experimental version of faster Z-Image-Turbo!

💪 Open-source Plans

• Release faster experimental version of Z-Image-Turbo.
• Release APEX-v0 version of Z-Image.
• Release APEX-v0 version of Qwen-Image-2512.
• Release large-scale training code.

APEX

APEX-Qwen-Image-2512 Visualization

2-NFE visualization of Qwen-Image-2512

Inference Demo

For ComfyUI users, please see https://github.com/smthemex/ComfyUI_TwinFlow.

Install the latest diffusers:

pip install git+https://github.com/huggingface/diffusers

Run inference demo inference.py:

python inference.py

We recommend to sample for 2~4 NFEs:

# 4 NFE config
sampler_config = {
    "sampling_steps": 4,
    "stochast_ratio": 1.0,
    "extrapol_ratio": 0.0,
    "sampling_order": 1,
    "time_dist_ctrl": [1.0, 1.0, 1.0],
    "rfba_gap_steps": [0.001, 0.5],
}

# 2 NFE config
sampler_config = {
    "sampling_steps": 2,
    "stochast_ratio": 1.0,
    "extrapol_ratio": 0.0,
    "sampling_order": 1,
    "time_dist_ctrl": [1.0, 1.0, 1.0],
    "rfba_gap_steps": [0.001, 0.6],
}

📖 Citation

@misc{liu2026selfadversarialstepgenerationcondition,
      title={Self-Adversarial One Step Generation via Condition Shifting}, 
      author={Deyuan Liu and Peng Sun and Yansen Han and Zhenglin Cheng and Chuyan Chen and Tao Lin},
      year={2026},
      eprint={2604.12322},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2604.12322}, 
}


@article{cheng2025twinflow,
  title={TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows},
  author={Cheng, Zhenglin and Sun, Peng and Li, Jianguo and Lin, Tao},
  journal={arXiv preprint arXiv:2512.05150},
  year={2025}
}

@misc{sun2025anystep,
  author = {Sun, Peng and Lin, Tao},
  note   = {GitHub repository},
  title  = {Any-step Generation via N-th Order Recursive Consistent Velocity Field Estimation},
  url    = {https://github.com/LINs-lab/RCGM},
  year   = {2025}
}

@article{sun2025unified,
  title = {Unified continuous generative models},
  author = {Sun, Peng and Jiang, Yi and Lin, Tao},
  journal = {arXiv preprint arXiv:2505.07447},
  year = {2025},
  url = {https://arxiv.org/abs/2505.07447},
  archiveprefix = {arXiv},
  eprint = {2505.07447},
  primaryclass = {cs.LG}
}

🤗 Acknowledgement

APEX is built upon TwinFlow, RCGM and UCGM.

Note: The LINs Lab has openings for PhD students for the Fall 2026/2027 intake. Interested candidates are encouraged to reach out.