Learning Illumination Control in Diffusion Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908996853563392 |
|---|---|
| author | Anand, Nishit Suri, Manan Metzler, Christopher Manocha, Dinesh Duraiswami, Ramani |
| author_facet | Anand, Nishit Suri, Manan Metzler, Christopher Manocha, Dinesh Duraiswami, Ramani |
| contents | Controlling illumination in images is essential for photography and visual content creation. While closed-source models have demonstrated impressive illumination control, open-source alternatives either require heavy control inputs like depth maps or do not release their data and code. We present a fully open-source and reproducible pipeline for learning illumination control in diffusion models. Our approach builds a data engine that transforms well-lit images into supervised training triplets consisting of a poorly-illuminated input image, a natural language lighting instruction, and a well-illuminated output image. We finetune a diffusion model on this data and demonstrate significant improvements over baseline SD 1.5, SDXL, and FLUX.1-dev models in perceptual similarity, structural similarity, and identity preservation. Our work provides a reproducible solution built entirely with open-source tools and publicly available data. We release all our code, data, and model weights publicly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_24877 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Illumination Control in Diffusion Models Anand, Nishit Suri, Manan Metzler, Christopher Manocha, Dinesh Duraiswami, Ramani Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing Controlling illumination in images is essential for photography and visual content creation. While closed-source models have demonstrated impressive illumination control, open-source alternatives either require heavy control inputs like depth maps or do not release their data and code. We present a fully open-source and reproducible pipeline for learning illumination control in diffusion models. Our approach builds a data engine that transforms well-lit images into supervised training triplets consisting of a poorly-illuminated input image, a natural language lighting instruction, and a well-illuminated output image. We finetune a diffusion model on this data and demonstrate significant improvements over baseline SD 1.5, SDXL, and FLUX.1-dev models in perceptual similarity, structural similarity, and identity preservation. Our work provides a reproducible solution built entirely with open-source tools and publicly available data. We release all our code, data, and model weights publicly. |
| title | Learning Illumination Control in Diffusion Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2604.24877 |