paper-with-me

홈 › Papers

Dense Text-to-Image Generation with Attention Modulation

2023-08-24 · ICCV 2023 1 · Yunji Kim, Jiyoung Lee, Jin-Hwa Kim, Jung-Woo Ha, Jun-Yan Zhu

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 training-free method that adapts a pre-trained text-to-image model to handle such dense captions while offering control over the scene layout. We first analyze the relationship between generated images' layouts and the pre-trained model's intermediate attention maps. Next, we develop an attention modulation method that guides objects to appear in specific regions according to layout guidance. Without requiring additional fine-tuning or datasets, we improve image generation performance given dense captions regarding both automatic and human evaluation scores. In addition, we achieve similar-quality visual results with models specifically trained with layout conditions.

📄 PDF Abstract BibTeX arXiv:2308.12964

Code (1)

naver-ai/densediffusion 공식 구현 pytorch

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

On-the-Fly Attention Modulation for Neural Generation

2021-01-02 · Findings (ACL) 2021 8 · Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang 외

Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from degeneration: the generated text is repetitive, generic, self-contradictory, and often lacks commonsense…

Language ModellingSentenceText Generation

Self-supervised Learning with Speech Modulation Dropout

2023-03-22 · Samik Sadhu, Hynek Hermansky

We show that training a multi-headed self-attention-based deep network to predict deleted, information-dense 2-8 Hz speech modulations over a 1.5-second section of a speech utterance is an effective way to make machines …

Automatic Speech RecognitionSelf-Supervised Learningspeech-recognitionSpeech Recognition

Rethinking Global Text Conditioning in Diffusion Transformers

2026-02-09 · Nikita Starodubcev, Daniil Pakhomov, Zongze Wu, Ilya Drobyshevskiy 외 arxiv

Diffusion transformers typically incorporate textual information via attention layers and a modulation mechanism using a pooled text embedding. Nevertheless, recent approaches discard modulation-based text conditioning a…

Video GenerationImage Editing

TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space

2025-01-21 · Daniel Garibi, Shahar Yadin, Roni Paiss, Omer Tov 외

We present TokenVerse -- a method for multi-concept personalization, leveraging a pre-trained text-to-image diffusion model. Our framework can disentangle complex visual elements and attributes from as little as a single…

Lightweight Image Enhancement Network for Mobile Devices Using Self-Feature Extraction and Dense Modulation

2022-05-02 · Sangwook Baek, Yongsup Park, Youngo Park, Jungmin Lee 외

Convolutional neural network (CNN) based image enhancement methods such as super-resolution and detail enhancement have achieved remarkable performances. However, amounts of operations including convolution and parameter…

Image EnhancementSuper-Resolution