English
Related papers

Related papers: Guiding a Diffusion Model by Swapping Its Tokens

200 papers

Classifier-Free Guidance (CFG) serves as the de facto control mechanism for conditional diffusion, yet high guidance scales notoriously induce oversaturation, texture artifacts, and structural collapse. We attribute this failure to a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Zexi Jia , Pengcheng Luo , Zhengyao Fang , Jinchao Zhang , Jie Zhou

Conditional image generative models hold considerable promise to produce infinite amounts of synthetic training data. Yet, recent progress in generation quality has come at the expense of generation diversity, limiting the utility of these…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Nicola Dall'Asen , Xiaofeng Zhang , Reyhane Askari Hemmat , Melissa Hall , Jakob Verbeek , Adriana Romero-Soriano , Michal Drozdzal

Text-to-image diffusion models like Stable Diffusion generate high-quality images from text, but lack a way to inject visual guidance (e.g. sketches, styles) at inference without retraining. Existing methods either require computationally…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Agata Żywot , Iason Skylitsis , Thijmen Nijdam , Zoe Tzifa-Kratira , Derck Prinzhorn , Konrad Szewczyk , Aritra Bhowmik

Diffusion models have achieved remarkable progress in image and audio generation, largely due to Classifier-Free Guidance. However, the choice of guidance scale remains underexplored: a fixed scale often fails to generalize across prompts…

Sound · Computer Science 2025-10-07 Xuanhao Zhang , Chang Li

Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptions. However, a significant limitation of these models is…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Mingyuan Zhou , Zhendong Wang , Huangjie Zheng , Hai Huang

Recent advances in text-to-image synthesis largely benefit from sophisticated sampling strategies and classifier-free guidance (CFG) to ensure high-quality generation. However, CFG's reliance on two forward passes, especially when combined…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Minghao Fu , Guo-Hua Wang , Xiaohao Chen , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang

Diffusion models have emerged as a formidable tool for training-free conditional generation.However, a key hurdle in inference-time guidance techniques is the need for compute-heavy backpropagation through the diffusion network for…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Nithin Gopalakrishnan Nair , Vishal M Patel

Generative models are transforming creative domains such as music generation, with inference-time strategies like Classifier-Free Guidance (CFG) playing a crucial role. However, CFG doubles inference cost while limiting originality and…

Diffusion models have emerged as powerful generative models for graph generation, yet their use for conditional graph generation remains a fundamental challenge. In particular, guiding diffusion models on graphs under arbitrary reward…

Machine Learning · Computer Science 2025-05-27 Victor M. Tenorio , Nicolas Zilberstein , Santiago Segarra , Antonio G. Marques

Diffusion-based editing models have emerged as a powerful tool for semantic image and video manipulation. However, existing models lack a mechanism for smoothly controlling the intensity of text-guided edits. In standard text-conditioned…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Alon Wolf , Chen Katzir , Kfir Aberman , Or Patashnik

Recent advances in diffusion models attempt to handle conditional generative tasks by utilizing a differentiable loss function for guidance without the need for additional training. While these methods achieved certain success, they often…

Machine Learning · Computer Science 2024-07-08 Lingxiao Yang , Shutong Ding , Yifan Cai , Jingyi Yu , Jingya Wang , Ye Shi

Text-conditioned molecular generation aims to translate natural-language descriptions into chemical structures, enabling scientists to specify functional groups, scaffolds, and physicochemical constraints without handcrafted rules.…

Machine Learning · Computer Science 2025-11-18 Lingxiao Li , Haobo Zhang , Bin Chen , Jiayu Zhou

In this paper, we present \textbf{\textit{FasterCache}}, a novel training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation. By analyzing existing cache-based methods, we observe that…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Zhengyao Lv , Chenyang Si , Junhao Song , Zhenyu Yang , Yu Qiao , Ziwei Liu , Kwan-Yee K. Wong

Guiding unconditional diffusion models typically requires either retraining with conditional inputs or per-step gradient computations (e.g., classifier-based guidance), both of which incur substantial computational overhead. We present a…

Machine Learning · Computer Science 2026-02-13 Qingsong Wang , Mikhail Belkin , Yusu Wang

Text-to-video diffusion models generate realistic videos, but often fail on prompts requiring fine-grained compositional understanding, such as relations between entities, attributes, actions, and motion directions. We hypothesize that…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Ariel Shaulov , Eitan Shaar , Amit Edenzon , Gal Chechik , Lior Wolf

Diffusion models have demonstrated strong generative performance when using guidance methods such as classifier-free guidance (CFG), which enhance output quality by modifying the sampling trajectory. These methods typically improve a target…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Kwanyoung Kim

Recent advancements in diffusion models have revolutionized generative modeling. However, the impressive and vivid outputs they produce often come at the cost of significant model scaling and increased computational demands. Consequently,…

Machine Learning · Computer Science 2025-04-03 Jincheng Zhong , Xiangcheng Zhang , Jianmin Wang , Mingsheng Long

Unconditional generation -- the problem of modeling data distribution without relying on human-annotated labels -- is a long-standing and fundamental challenge in generative models, creating a potential of learning from large-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Tianhong Li , Dina Katabi , Kaiming He

Diffusion models (DMs) have demonstrated an unparalleled ability to create diverse and high-fidelity images from text prompts. However, they are also well-known to vary substantially regarding both prompt adherence and quality. Negative…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Alakh Desai , Nuno Vasconcelos

Classifier-free guidance is an effective sampling technique in diffusion models that has been widely adopted. The main idea is to extrapolate the model in the direction of text guidance and away from null-text guidance. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2023-08-07 Jing Zhao , Heliang Zheng , Chaoyue Wang , Long Lan , Wanrong Huang , Wenjing Yang
‹ Prev 1 4 5 6 7 8 10 Next ›