Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.19967 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910624466862080 |
|---|---|
| author | Zhuang, Chenyi Hu, Ying Gao, Pan |
| author_facet | Zhuang, Chenyi Hu, Ying Gao, Pan |
| contents | Text-to-image diffusion models particularly Stable Diffusion, have revolutionized the field of computer vision. However, the synthesis quality often deteriorates when asked to generate images that faithfully represent complex prompts involving multiple attributes and objects. While previous studies suggest that blended text embeddings lead to improper attribute binding, few have explored this in depth. In this work, we critically examine the limitations of the CLIP text encoder in understanding attributes and investigate how this affects diffusion models. We discern a phenomenon of attribute bias in the text space and highlight a contextual issue in padding embeddings that entangle different concepts. We propose \textbf{Magnet}, a novel training-free approach to tackle the attribute binding problem. We introduce positive and negative binding vectors to enhance disentanglement, further with a neighbor strategy to increase accuracy. Extensive experiments show that Magnet significantly improves synthesis quality and binding accuracy with negligible computational cost, enabling the generation of unconventional and unnatural concepts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19967 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function Zhuang, Chenyi Hu, Ying Gao, Pan Computer Vision and Pattern Recognition Text-to-image diffusion models particularly Stable Diffusion, have revolutionized the field of computer vision. However, the synthesis quality often deteriorates when asked to generate images that faithfully represent complex prompts involving multiple attributes and objects. While previous studies suggest that blended text embeddings lead to improper attribute binding, few have explored this in depth. In this work, we critically examine the limitations of the CLIP text encoder in understanding attributes and investigate how this affects diffusion models. We discern a phenomenon of attribute bias in the text space and highlight a contextual issue in padding embeddings that entangle different concepts. We propose \textbf{Magnet}, a novel training-free approach to tackle the attribute binding problem. We introduce positive and negative binding vectors to enhance disentanglement, further with a neighbor strategy to increase accuracy. Extensive experiments show that Magnet significantly improves synthesis quality and binding accuracy with negligible computational cost, enabling the generation of unconventional and unnatural concepts. |
| title | Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.19967 |