paper-with-me

홈 › Papers

EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts

2024-06-13 · Yucheng Han, Rui Wang, Chi Zhang, Juntao Hu, Pei Cheng, Bin Fu, Hanwang Zhang

Recent advancements in image generation have enabled the creation of high-quality images from text conditions. However, when facing multi-modal conditions, such as text combined with reference appearances, existing methods struggle to balance multiple conditions effectively, typically showing a preference for one modality over others. To address this challenge, we introduce EMMA, a novel image generation model accepting multi-modal prompts built upon the state-of-the-art text-to-image (T2I) diffusion model, ELLA. EMMA seamlessly incorporates additional modalities alongside text to guide image generation through an innovative Multi-modal Feature Connector design, which effectively integrates textual and supplementary modal information using a special attention mechanism. By freezing all parameters in the original T2I diffusion model and only adjusting some additional layers, we reveal an interesting finding that the pre-trained T2I diffusion model can secretly accept multi-modal prompts. This interesting property facilitates easy adaptation to different existing frameworks, making EMMA a flexible and effective tool for producing personalized and context-aware images and even videos. Additionally, we introduce a strategy to assemble learned EMMA modules to produce images conditioned on multiple modalities simultaneously, eliminating the need for additional training with mixed multi-modal prompts. Extensive experiments demonstrate the effectiveness of EMMA in maintaining high fidelity and detail in generated images, showcasing its potential as a robust solution for advanced multi-modal conditional image generation tasks.

📄 PDF Abstract BibTeX arXiv:2406.09162

Code (1)

tencentqqgylab/ella pytorch

Tasks

Conditional Image GenerationImage 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

Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation

2026-06-29 · Shihao Zhang, Yuguang Yan, Junzhe Zhang, Wei Zhao 외 arxiv

Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve realism. These signals, however, incur su…

Text-to-Video Generation

Your Pre-trained Diffusion Model Secretly Knows Restoration

2026-04-06 · Sudarshan Rajagopalan, Vishal M. Patel arxiv

Pre-trained diffusion models have enabled significant advancements in All-in-One Restoration (AiOR), offering improved perceptual quality and generalization. However, diffusion-based restoration methods primarily rely on…

Your Diffusion Model is Secretly a Zero-Shot Classifier

2023-03-28 · ICCV 2023 1 · Alexander C. Li, Mihir Prabhudesai, Shivam Duggal, Ellis Brown 외

The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a staggering variety of prompts and exhib…

Domain GeneralizationFine-Grained Image ClassificationImage ClassificationImage Generation+5

Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model

2022-08-16 · Xiulong Yang, Sheng-Min Shih, Yinlin Fu, Xiaoting Zhao 외

Diffusion Denoising Probability Models (DDPM) and Vision Transformer (ViT) have demonstrated significant progress in generative tasks and discriminative tasks, respectively, and thus far these models have largely been de…

DenoisingImage ClassificationImage Generation

Your diffusion model secretly knows the dimension of the data manifold

2022-12-23 · Jan Stanczuk, Georgios Batzolis, Teo Deveney, Carola-Bibiane Schönlieb

In this work, we propose a novel framework for estimating the dimension of the data manifold using a trained diffusion model. A diffusion model approximates the score function i.e. the gradient of the log density of a no…