English
Related papers

Related papers: ToLo: A Two-Stage, Training-Free Layout-To-Image G…

200 papers

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Yusuf Dalva , Guocheng Gordon Qian , Maya Goldenberg , Tsai-Shien Chen , Kfir Aberman , Sergey Tulyakov , Pinar Yanardag , Kuan-Chieh Jackson Wang

Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Yang Li , Songlin Yang , Xiaoxuan Han , Wei Wang , Jing Dong , Yueming Lyu , Ziyu Xue

Diffusion-driven text-to-image (T2I) generation has achieved remarkable advancements in recent years. To further improve T2I models' capability in numerical and spatial reasoning, layout is employed as an intermedium to bridge large…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yuhao Jia , Wenhan Tan

Modern diffusion models, particularly those utilizing a Transformer-based UNet for denoising, rely heavily on self-attention operations to manage complex spatial relationships, thus achieving impressive generation performance. However, this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 Songhua Liu , Weihao Yu , Zhenxiong Tan , Xinchao Wang

The crux of text-to-image synthesis stems from the difficulty of preserving the cross-modality semantic consistency between the input text and the synthesized image. Typical methods, which seek to model the text-to-image mapping directly,…

Computer Vision and Pattern Recognition · Computer Science 2022-08-15 Jiadong Liang , Wenjie Pei , Feng Lu

Recent advancements in diffusion models have enabled a wide range of works exploiting their ability to generate high-volume, high-quality data for use in various downstream tasks. One subclass of such models, dubbed Layout-to-Image…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Ahmed Abdullah , Nikolas Ebert , Oliver Wasenmüller

Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Yunji Kim , Jiyoung Lee , Jin-Hwa Kim , Jung-Woo Ha , Jun-Yan Zhu

Typical layout-to-image synthesis (LIS) models generate images for a closed set of semantic classes, e.g., 182 common objects in COCO-Stuff. In this work, we explore the freestyle capability of the model, i.e., how far can it generate…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Han Xue , Zhiwu Huang , Qianru Sun , Li Song , Wenjun Zhang

Tokenizing images into compact visual representations is a key step in learning efficient and high-quality image generative models. We present a simple diffusion tokenizer (DiTo) that learns compact visual representations for image…

Computer Vision and Pattern Recognition · Computer Science 2025-01-31 Yinbo Chen , Rohit Girdhar , Xiaolong Wang , Sai Saketh Rambhatla , Ishan Misra

Despite recent advances in text-to-image generation, using synthetically generated data seldom brings a significant boost in performance for supervised learning. Oftentimes, synthetic datasets do not faithfully recreate the data…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Jae Myung Kim , Stephan Alaniz , Cordelia Schmid , Zeynep Akata

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Yuki Endo

In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised homography network. In the generation phase, given an…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Hai Jiang , Haipeng Li , Songchen Han , Haoqiang Fan , Bing Zeng , Shuaicheng Liu

Recent studies have demonstrated that the forward diffusion process is crucial for the effectiveness of diffusion models in terms of generative quality and sampling efficiency. We propose incorporating an analytical image attenuation…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Yuhang Huang , Zheng Qin , Xinwang Liu , Kai Xu

Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity. Plug-and-play token reduction methods like ToMeSD and ToFu reduce FLOPs by merging redundant tokens in…

Machine Learning · Computer Science 2025-12-02 Wenbo Lu , Shaoyi Zheng , Yuxuan Xia , Shengjie Wang

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

Computer Vision and Pattern Recognition · Computer Science 2023-09-13 Yunhao Ge , Jiashu Xu , Brian Nlong Zhao , Neel Joshi , Laurent Itti , Vibhav Vineet

We introduce a novel sketch-to-image tool that aligns with the iterative refinement process of artists. Our tool lets users sketch blocking strokes to coarsely represent the placement and form of objects and detail strokes to refine their…

Graphics · Computer Science 2024-10-28 Vishnu Sarukkai , Lu Yuan , Mia Tang , Maneesh Agrawala , Kayvon Fatahalian

Generating long videos using pre-trained video diffusion models, which are typically trained on short clips, presents a significant challenge. Directly applying these models for long-video inference often leads to a notable degradation in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Jiahao Tian , Chenxi Song , Wei Cheng , Chi Zhang

Text-to-image diffusion has attracted vast attention due to its impressive image-generation capabilities. However, when it comes to human-centric text-to-image generation, particularly in the context of faces and hands, the results often…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Jie Zhu , Yixiong Chen , Mingyu Ding , Ping Luo , Leye Wang , Jingdong Wang

Interleaved text-image generation aims to jointly produce coherent visual frames and aligned textual descriptions within a single sequence, enabling tasks such as style transfer, compositional synthesis, and procedural tutorials. We present…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Mingcheng Ye , Jiaming Liu , Yiren Song

Current large-scale generative models have impressive efficiency in generating high-quality images based on text prompts. However, they lack the ability to precisely control the size and position of objects in the generated image. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-04-27 Jiafeng Mao , Xueting Wang