DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation

arXiv:2402.11929v1 Announce Type: new
Abstract: This paper presents a novel method for exerting fine-grained lighting control during text-driven diffusion-based image generation. While existing diffusion models already have the ability to generate images under any lighting condition, without additional guidance these models tend to correlate image content and lighting. Moreover, text prompts lack the necessary expressional power to describe detailed lighting setups. To provide the content creator with fine-grained control over the lighting during image generation, we augment the text-prompt with …

abstract arxiv control cs.cv cs.gr diffusion diffusion models fine-grained generate guidance image image generation images lighting novel paper prompts text type