English
Related papers

Related papers: Guiding a Diffusion Transformer with the Internal …

200 papers

Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with quadratic…

Computer Vision and Pattern Recognition · Computer Science 2024-11-28 Lianghui Zhu , Zilong Huang , Bencheng Liao , Jun Hao Liew , Hanshu Yan , Jiashi Feng , Xinggang Wang

Recent advances have significantly improved the training efficiency of diffusion transformers. However, these techniques have largely been studied in isolation, leaving unexplored the potential synergies from combining multiple approaches.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Swayam Bhanded

In light of the widespread success of generative models, a significant amount of research has gone into speeding up their sampling time. However, generative models are often sampled multiple times to obtain a diverse set incurring a cost…

Machine Learning · Computer Science 2023-11-27 Gabriele Corso , Yilun Xu , Valentin de Bortoli , Regina Barzilay , Tommi Jaakkola

Diffusion models have emerged as the dominant paradigm for high-quality image generation, yet their computational expense remains substantial due to iterative denoising. Classifier-Free Guidance (CFG) significantly enhances generation…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Ruitong Sun , Tianze Yang , Wei Niu , Jin Sun

Recent studies have demonstrated that diffusion models are capable of generating high-quality samples, but their quality heavily depends on sampling guidance techniques, such as classifier guidance (CG) and classifier-free guidance (CFG).…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Donghoon Ahn , Hyoungwon Cho , Jaewon Min , Wooseok Jang , Jungwoo Kim , SeonHwa Kim , Hyun Hee Park , Kyong Hwan Jin , Seungryong Kim

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

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…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Haosen Li , Wenshuo Chen , Lei Wang , Shaofeng Liang , Bowen Tian , Soning Lai , Yutao Yue

Classifier-Free Guidance (CFG) has been a default technique in various visual generative models, yet it requires inference from both conditional and unconditional models during sampling. We propose to build visual models that are free from…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Huayu Chen , Kai Jiang , Kaiwen Zheng , Jianfei Chen , Hang Su , Jun Zhu

This study addresses the challenge of, without training or fine-tuning, controlling the global color aspect of images generated with a diffusion model. We rewrite the guidance equations to ensure that the outputs are closer to a known color…

Computer Vision and Pattern Recognition · Computer Science 2024-04-11 Tom Bordin , Thomas Maugey

Recent progress in generative modeling has enabled high-quality visual synthesis with diffusion-based frameworks, supporting controllable sampling and large-scale training. Inference-time guidance methods such as classifier-free and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Wenqiang Zu , Shenghao Xie , Bo Lei , Lei Ma

Classifier-free guidance (CFG) is crucial for improving both generation quality and alignment between the input condition and final output in diffusion models. While a high guidance scale is generally required to enhance these aspects, it…

Machine Learning · Computer Science 2025-06-04 Seyedmorteza Sadat , Otmar Hilliges , Romann M. Weber

While diffusion models have made remarkable progress in image generation, their outputs can still appear unrealistic and lack fine details, especially when using fewer number of neural function evaluations (NFEs) or lower guidance scales.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Seyedmorteza Sadat , Farnood Salehi , Romann M. Weber

We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Shulei Wang , Wang Lin , Hai Huang , Hanting Wang , Sihang Cai , WenKang Han , Tao Jin , Jingyuan Chen , Jiacheng Sun , Jieming Zhu , Zhou Zhao

Image diffusion models are trained on independently sampled static images. While this is the bedrock task protocol in generative modeling, capturing the temporal world through the lens of static snapshots is information-deficient by design.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-05 Juhun Lee , Simon S. Woo

Diffusion models have demonstrated significant promise in various generative tasks; however, they often struggle to satisfy challenging constraints. Our approach addresses this limitation by rethinking training-free loss-guided diffusion…

Machine Learning · Computer Science 2024-11-19 William Huang , Yifeng Jiang , Tom Van Wouwe , C. Karen Liu

Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Zechuan Zhang , Ji Xie , Yu Lu , Zongxin Yang , Yi Yang

Dataset distillation enables efficient training by distilling the information of large-scale datasets into significantly smaller synthetic datasets. Diffusion based paradigms have emerged in recent years, offering novel perspectives for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Qichao Wang , Yunhong Lu , Hengyuan Cao , Junyi Zhang , Min Zhang

Score-based generative models require guidance in order to generate plausible, on-manifold samples. The most popular guidance method, Classifier-Free Guidance (CFG), is only applicable in settings with labeled data and requires training an…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Eric Yeats , Darryl Hannan , Wilson Fearn , Timothy Doster , Henry Kvinge , Scott Mahan

We propose continuous adversarial flow models, a type of continuous-time flow model trained with an adversarial objective. Unlike flow matching, which uses a fixed mean-squared-error criterion, our approach introduces a learned…

Machine Learning · Computer Science 2026-04-14 Shanchuan Lin , Ceyuan Yang , Zhijie Lin , Hao Chen , Haoqi Fan

Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards…

Machine Learning · Statistics 2024-10-17 Yingqing Guo , Hui Yuan , Yukang Yang , Minshuo Chen , Mengdi Wang