[ICLR2026] S²-Guidance: Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models

Chubin Chen¹, Jiashu Zhu², Xiaokun Feng^2,3, Nisha Huang¹
Meiqi Wu^2,3, Fangyuan Mao², Jiahong Wu^2,‡, Xiangxiang Chu², Xiu Li<sup>1,†

1</sup>Tsinghua University     ²AMAP, Alibaba Group     ³CASIA
^†Corresponding author.     ^‡Project lead.

       

🔥 Updates

• [2025/08] Our paper is available on arXiv and the project page is live!
• [2026/01]: 🎉🎉🎉 Our paper is accepted by ICLR 2026!
• [Coming Soon] Code will be released in few days!

📣 Overview

We propose S²-Guidance, a novel method that leverages stochastic block-dropping during the forward process to construct sub-networks, effectively guiding the model away from potential low-quality predictions and toward high-quality outputs. Extensive qualitative and quantitative experiments on text-to-image and text-to-video generation tasks demonstrate that S²-Guidance delivers superior performance, consistently surpassing CFG and other advanced guidance strategies.

🎉 Results

Here are some examples comparing the results from standard Classifier-free Guidance (CFG) with our S²-Guidance. Our method consistently produces higher-fidelity and more coherent results.

Text-to-Image Generation

Prompt: "The bold dramatic strokes of the painter's brush created a stunning abstract masterpiece a work of emotional depth and intensity."

CFG	Ours (S²-Guidance)

---

Prompt: "A floating castle above the clouds, with 'S2 Guidance Is All You Need' swirling in the mist."

CFG	Ours (S²-Guidance)

---

Prompt: "A woman is holding a bouquet of balloons and celebrating a birthday."

CFG	Ours (S²-Guidance)

---

Prompt: "A red book and an ivory sheep."

CFG	Ours (S²-Guidance)

---

Prompt: "A cat sitting besides a rocket on a planet with a lot of cactuses."

CFG	Ours (S²-Guidance)

---

Prompt: "A woman sitting under an umbrella in the middle of a restaurant."

CFG	Ours (S²-Guidance)

Text-to-Video Generation

Prompt: "A breathtaking close-up of a woman frozen in time as golden threads of light weave around her face, creating dynamic flowing patterns of energy amidst glowing particles."

CFG baseline_video1.mp4

Ours (S²-Guidance) ours_video1.mp4

---

Prompt: "An astronaut flying in space."

CFG baseline_video2.mp4

Ours (S²-Guidance) ours_video2.mp4

---

Prompt: "A car accelerating to gain speed."

CFG baseline_video3.mp4

Ours (S²-Guidance) ours_video3.mp4

---

Prompt: "A close-up of a beautiful woman's face with colored powder exploding around her, creating an abstract splash of vibrant hues."

CFG baseline_video_4.mp4

Ours (S²-Guidance) ours_video_4.mp4

User Study

Quantitative Results

HPSV2.1 & T2I-ComBench

VBench

🙏 Acknowledgements

This work is built upon many amazing open-source projects. We would like to thank the developers of Diffusers, PyTorch, and other related libraries for their contributions to the community.

📜 Citation

If you find our work useful for your research, please feel free to leave a star⭐️⭐️⭐️ and cite our paper:

@misc{chen2025s2guidancestochasticselfguidance,
      title={S$^2$-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models}, 
      author={Chubin Chen and Jiashu Zhu and Xiaokun Feng and Nisha Huang and Meiqi Wu and Fangyuan Mao and Jiahong Wu and Xiangxiang Chu and Xiu Li},
      year={2025},
      eprint={2508.12880},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2508.12880}, 
}