Rich Human Feedback for Text-to-Image Generation

arXiv:2312.10240v2 Announce Type: replace
Abstract: Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as artifacts/implausibility, misalignment with text descriptions, and low aesthetic quality. Inspired by the success of Reinforcement Learning with Human Feedback (RLHF) for large language models, prior works collected human-provided scores as feedback on generated images and trained a reward model to improve the …

arxiv cs.cv feedback human human feedback image image generation text text-to-image type