Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.13547 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911514700546048 |
|---|---|
| author | Butt, Muhammad Atif Hernandez, Diego Gomez-Villa, Alexandra Wang, Kai Vazquez-Corral, Javier Van De Weijer, Joost |
| author_facet | Butt, Muhammad Atif Hernandez, Diego Gomez-Villa, Alexandra Wang, Kai Vazquez-Corral, Javier Van De Weijer, Joost |
| contents | Text-to-image diffusion models excel at generating images from natural language descriptions, yet fail to interpret numerical colors such as hex codes (#FF5733) and RGB values (rgb(255,87,51)). This limitation stems from subword tokenization, which fragments color codes into semantically meaningless tokens that text encoders cannot map to coherent color representations. We present NumColor, that enables precise numerical color control across multiple diffusion architectures. NumColor comprises two components: a Color Token Aggregator that detects color specifications regardless of tokenization, and a ColorBook containing 6,707 learnable embeddings that map colors to embedding space of text encoder in perceptually uniform CIE Lab space. We introduce two auxiliary losses, directional alignment and interpolation consistency, to enforce geometric correspondence between Lab and embedding spaces, enabling smooth color interpolation. To train the ColorBook, we construct NumColor-Data, a synthetic dataset of 500K rendered images with unambiguous color-to-pixel correspondence, eliminating the annotation ambiguity inherent in photographic datasets. Although trained solely on FLUX, NumColor transfers zero-shot to SD3, SD3.5, PixArt-α, and PixArt-Σ without model-specific adaptation. NumColor improves numerical color accuracy by 4-9x across five models, while simultaneously improving color harmony scores by 10-30x on GenColorBench benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13547 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NumColor: Precise Numeric Color Control in Text-to-Image Generation Butt, Muhammad Atif Hernandez, Diego Gomez-Villa, Alexandra Wang, Kai Vazquez-Corral, Javier Van De Weijer, Joost Computer Vision and Pattern Recognition Text-to-image diffusion models excel at generating images from natural language descriptions, yet fail to interpret numerical colors such as hex codes (#FF5733) and RGB values (rgb(255,87,51)). This limitation stems from subword tokenization, which fragments color codes into semantically meaningless tokens that text encoders cannot map to coherent color representations. We present NumColor, that enables precise numerical color control across multiple diffusion architectures. NumColor comprises two components: a Color Token Aggregator that detects color specifications regardless of tokenization, and a ColorBook containing 6,707 learnable embeddings that map colors to embedding space of text encoder in perceptually uniform CIE Lab space. We introduce two auxiliary losses, directional alignment and interpolation consistency, to enforce geometric correspondence between Lab and embedding spaces, enabling smooth color interpolation. To train the ColorBook, we construct NumColor-Data, a synthetic dataset of 500K rendered images with unambiguous color-to-pixel correspondence, eliminating the annotation ambiguity inherent in photographic datasets. Although trained solely on FLUX, NumColor transfers zero-shot to SD3, SD3.5, PixArt-α, and PixArt-Σ without model-specific adaptation. NumColor improves numerical color accuracy by 4-9x across five models, while simultaneously improving color harmony scores by 10-30x on GenColorBench benchmark. |
| title | NumColor: Precise Numeric Color Control in Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.13547 |