Diffusion models have achieved remarkable success in synthesizing complex static and temporal visuals, a breakthrough largely driven by Classifier-Free Guidance (CFG). However, despite its pivotal role in aligning generated content with textual prompts, standard CFG relies on a globally uniform scalar. This homogeneous amplification traps models in a well-documented "detail-artifact dilemma": low guidance scales fail to inject intricate semantics, while high scales inevitably cause structural degradation, color over-saturation, and temporal inconsistencies in videos. In this paper, we expose the physical root of this flaw through the lens of differential geometry. By analyzing Tweedie's Formula, we reveal that CFG intrinsically performs a tangential linear extrapolation. Because the natural data manifold is highly curved, this uniform linear step introduces a severe orthogonal deviation. To keep the generation trajectory safely bounded, we formulate a theoretical upper bound for spatial and adaptive guidance. Based on these geometric insights, we propose Spatial Adaptive Multi Guidance (SAMG), a training-free and virtually zero-cost sampling algorithm. SAMG dynamically computes point-wise conditional guidance energy, applying a conservative minimum scale to high-energy boundary regions to preserve delicate micro-textures, while deploying an aggressive maximum scale in low-energy regions to maximize semantic injection. Extensive experiments across diverse image (SD 1.5, SDXL, SD3.5 Medium) and video (CogVideoX, ModelScope) architectures demonstrate that SAMG effectively resolves the detail-artifact dilemma, achieving superior semantic alignment, structural integrity, and temporal smoothness without any computational overhead.
SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score
Department of Computer Science and Engineering, The Chinese University of Hong Kong(计算机科学与工程系,香港中文大学);Department of Information Engineering, The Chinese University of Hong Kong(信息工程系,香港中文大学)
Language-Grounded Multi-Domain Image Translation via Semantic Difference Guidance
Department of Artificial Intelligence, Chung-Ang University(人工智能系, Chung-Ang 大学);Hyundai Mobis;Korea Advanced Institute of Science and Technology(韩国科学技术院)
Delta Rectified Flow Sampling for Text-to-Image Editing
Harvard AI and Robotics Lab, Harvard University(哈佛大学人工智能与机器人实验室);Computer Science Department, Harvard University(哈佛大学计算机科学系);Multimodal Intelligence and Perception Lab, DGIST(大邱庆北科学技术院多模态智能与感知实验室);Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University(哈佛大学肯普纳自然与人工智能研究所)
Self-Guidance: Boosting Flow and Diffusion Generation on Their Own
Zhejiang University(浙江大学);MAPLE Lab, Westlake University(西湖大学MAPLE实验室);Peking University(北京大学);Institute of Advanced Technology, Westlake Institute for Advanced Study(西湖研究院先进技术研究所)
Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));Cogniser Information Technology(Cogniser信息科技)
MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion
Fudan University(复旦大学);Shanghai Collaborative Innovation Center of Intelligent Visual Computing(上海智能视觉计算协同创新中心);Microsoft Research Asia(微软亚洲研究院);Carnegie Mellon University(卡内基梅隆大学);Huya Inc.(虎牙公司)
Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance
CMAP, Ecole Polytechnique(高等理工学院CMAP);Institute of Foundation Models(基础模型研究所);MBZUAI(穆扎夫技术研究院);EPITA;Sorbonne University(索邦大学);Lagrange Mathematics and Computing Research Center(拉格朗日数学与计算研究中心);EPITA Research Lab(EPITA研究实验室);KTH Royal Institute of Technology(皇家理工学院)
Mitigating Exposure Bias in Discriminator Guided Diffusion Models
Artificial Intelligence and Learning Systems Laboratory(人工智能与学习系统实验室);School of Electrical and Computer Engineering(电气与计算机工程学院);National Technical University of Athens(雅典国立技术大学)