Scribble-Guided Diffusion for Training-free Text-to-Image Generation
This addresses the issue of precise spatial guidance in text-to-image generation for users, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of text-to-image diffusion models struggling to capture user intent by proposing Scribble-Guided Diffusion, which uses user-provided scribbles for spatial guidance, resulting in significant improvements in spatial control and consistency on the PASCAL-Scribble dataset.
Recent advancements in text-to-image diffusion models have demonstrated remarkable success, yet they often struggle to fully capture the user's intent. Existing approaches using textual inputs combined with bounding boxes or region masks fall short in providing precise spatial guidance, often leading to misaligned or unintended object orientation. To address these limitations, we propose Scribble-Guided Diffusion (ScribbleDiff), a training-free approach that utilizes simple user-provided scribbles as visual prompts to guide image generation. However, incorporating scribbles into diffusion models presents challenges due to their sparse and thin nature, making it difficult to ensure accurate orientation alignment. To overcome these challenges, we introduce moment alignment and scribble propagation, which allow for more effective and flexible alignment between generated images and scribble inputs. Experimental results on the PASCAL-Scribble dataset demonstrate significant improvements in spatial control and consistency, showcasing the effectiveness of scribble-based guidance in diffusion models. Our code is available at https://github.com/kaist-cvml-lab/scribble-diffusion.