Draw Like an Artist: Complex Scene Generation with Diffusion Model via Composition, Painting, and Retouching
원문 초록
Recent advances in text-to-image diffusion models have demonstrated impressive capabilities in image quality. However, complex scene generation remains relatively unexplored, and even the definition of `complex scene' itself remains unclear. In this paper, we address this gap by providing a precise definition of complex scenes and introducing a set of Complex Decomposition Criteria (CDC) based on this definition. Inspired by the artists painting process, we propose a training-free diffusion framework called Complex Diffusion (CxD), which divides the process into three stages: composition, painting, and retouching. Our method leverages the powerful chain-of-thought capabilities of large language models (LLMs) to decompose complex prompts based on CDC and to manage composition and layout. We then develop an attention modulation method that guides simple prompts to specific regions to complete the complex scene painting. Finally, we inject the detailed output of the LLM into a retouching model to enhance the image details, thus implementing the retouching stage. Extensive experiments demonstrate that our method outperforms previous SOTA approaches, significantly improving the generation of high-quality, semantically consistent, and visually diverse images for complex scenes, even with intricate prompts.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
$I^{2}$-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation
3D Scene Generation: A Survey
Steerable Scene Generation with Post Training and Inference-Time Search
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.