SEGA: Instructing Text-to-Image Models using Semantic Guidance
This provides incremental improvements for users of text-to-image models by offering more precise control over image generation, though it builds on existing classifier-free guidance methods.
The paper tackles the problem of limited semantic control in text-to-image diffusion models by introducing semantic guidance (SEGA), which enables users to steer the diffusion process for subtle edits, composition changes, and style adjustments, demonstrating effectiveness across models like Stable Diffusion and Paella.
Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. However, achieving one-shot generation that aligns with the user's intent is nearly impossible, yet small changes to the input prompt often result in very different images. This leaves the user with little semantic control. To put the user in control, we show how to interact with the diffusion process to flexibly steer it along semantic directions. This semantic guidance (SEGA) generalizes to any generative architecture using classifier-free guidance. More importantly, it allows for subtle and extensive edits, changes in composition and style, as well as optimizing the overall artistic conception. We demonstrate SEGA's effectiveness on both latent and pixel-based diffusion models such as Stable Diffusion, Paella, and DeepFloyd-IF using a variety of tasks, thus providing strong evidence for its versatility, flexibility, and improvements over existing methods.