Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2403.05135 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913257978068992 |
|---|---|
| author | Hu, Xiwei Wang, Rui Fang, Yixiao Fu, Bin Cheng, Pei Yu, Gang |
| author_facet | Hu, Xiwei Wang, Rui Fang, Yixiao Fu, Bin Cheng, Pei Yu, Gang |
| contents | Diffusion models have demonstrated remarkable performance in the domain of text-to-image generation. However, most widely used models still employ CLIP as their text encoder, which constrains their ability to comprehend dense prompts, encompassing multiple objects, detailed attributes, complex relationships, long-text alignment, etc. In this paper, we introduce an Efficient Large Language Model Adapter, termed ELLA, which equips text-to-image diffusion models with powerful Large Language Models (LLM) to enhance text alignment without training of either U-Net or LLM. To seamlessly bridge two pre-trained models, we investigate a range of semantic alignment connector designs and propose a novel module, the Timestep-Aware Semantic Connector (TSC), which dynamically extracts timestep-dependent conditions from LLM. Our approach adapts semantic features at different stages of the denoising process, assisting diffusion models in interpreting lengthy and intricate prompts over sampling timesteps. Additionally, ELLA can be readily incorporated with community models and tools to improve their prompt-following capabilities. To assess text-to-image models in dense prompt following, we introduce Dense Prompt Graph Benchmark (DPG-Bench), a challenging benchmark consisting of 1K dense prompts. Extensive experiments demonstrate the superiority of ELLA in dense prompt following compared to state-of-the-art methods, particularly in multiple object compositions involving diverse attributes and relationships. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05135 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment Hu, Xiwei Wang, Rui Fang, Yixiao Fu, Bin Cheng, Pei Yu, Gang Computer Vision and Pattern Recognition Diffusion models have demonstrated remarkable performance in the domain of text-to-image generation. However, most widely used models still employ CLIP as their text encoder, which constrains their ability to comprehend dense prompts, encompassing multiple objects, detailed attributes, complex relationships, long-text alignment, etc. In this paper, we introduce an Efficient Large Language Model Adapter, termed ELLA, which equips text-to-image diffusion models with powerful Large Language Models (LLM) to enhance text alignment without training of either U-Net or LLM. To seamlessly bridge two pre-trained models, we investigate a range of semantic alignment connector designs and propose a novel module, the Timestep-Aware Semantic Connector (TSC), which dynamically extracts timestep-dependent conditions from LLM. Our approach adapts semantic features at different stages of the denoising process, assisting diffusion models in interpreting lengthy and intricate prompts over sampling timesteps. Additionally, ELLA can be readily incorporated with community models and tools to improve their prompt-following capabilities. To assess text-to-image models in dense prompt following, we introduce Dense Prompt Graph Benchmark (DPG-Bench), a challenging benchmark consisting of 1K dense prompts. Extensive experiments demonstrate the superiority of ELLA in dense prompt following compared to state-of-the-art methods, particularly in multiple object compositions involving diverse attributes and relationships. |
| title | ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.05135 |