Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917720493129728 |
|---|---|
| author | Liu, Zeyu Liang, Weicong Liang, Zhanhao Luo, Chong Li, Ji Huang, Gao Yuan, Yuhui |
| author_facet | Liu, Zeyu Liang, Weicong Liang, Zhanhao Luo, Chong Li, Ji Huang, Gao Yuan, Yuhui |
| contents | Visual text rendering poses a fundamental challenge for contemporary text-to-image generation models, with the core problem lying in text encoder deficiencies. To achieve accurate text rendering, we identify two crucial requirements for text encoders: character awareness and alignment with glyphs. Our solution involves crafting a series of customized text encoder, Glyph-ByT5, by fine-tuning the character-aware ByT5 encoder using a meticulously curated paired glyph-text dataset. We present an effective method for integrating Glyph-ByT5 with SDXL, resulting in the creation of the Glyph-SDXL model for design image generation. This significantly enhances text rendering accuracy, improving it from less than $20\%$ to nearly $90\%$ on our design image benchmark. Noteworthy is Glyph-SDXL's newfound ability for text paragraph rendering, achieving high spelling accuracy for tens to hundreds of characters with automated multi-line layouts. Finally, through fine-tuning Glyph-SDXL with a small set of high-quality, photorealistic images featuring visual text, we showcase a substantial improvement in scene text rendering capabilities in open-domain real images. These compelling outcomes aim to encourage further exploration in designing customized text encoders for diverse and challenging tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_09622 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering Liu, Zeyu Liang, Weicong Liang, Zhanhao Luo, Chong Li, Ji Huang, Gao Yuan, Yuhui Computer Vision and Pattern Recognition Visual text rendering poses a fundamental challenge for contemporary text-to-image generation models, with the core problem lying in text encoder deficiencies. To achieve accurate text rendering, we identify two crucial requirements for text encoders: character awareness and alignment with glyphs. Our solution involves crafting a series of customized text encoder, Glyph-ByT5, by fine-tuning the character-aware ByT5 encoder using a meticulously curated paired glyph-text dataset. We present an effective method for integrating Glyph-ByT5 with SDXL, resulting in the creation of the Glyph-SDXL model for design image generation. This significantly enhances text rendering accuracy, improving it from less than $20\%$ to nearly $90\%$ on our design image benchmark. Noteworthy is Glyph-SDXL's newfound ability for text paragraph rendering, achieving high spelling accuracy for tens to hundreds of characters with automated multi-line layouts. Finally, through fine-tuning Glyph-SDXL with a small set of high-quality, photorealistic images featuring visual text, we showcase a substantial improvement in scene text rendering capabilities in open-domain real images. These compelling outcomes aim to encourage further exploration in designing customized text encoders for diverse and challenging tasks. |
| title | Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.09622 |