TheaterGen: Character Management with LLM for Consistent Multi-turn Image Generation

arXiv:2404.18919v1 Announce Type: new
Abstract: Recent advances in diffusion models can generate high-quality and stunning images from text. However, multi-turn image generation, which is of high demand in real-world scenarios, still faces challenges in maintaining semantic consistency between images and texts, as well as contextual consistency of the same subject across multiple interactive turns. To address this issue, we introduce TheaterGen, a training-free framework that integrates large language models (LLMs) and text-to-image (T2I) models to provide the capability of multi-turn …

abstract advances arxiv challenges consistent cs.cv demand diffusion diffusion models generate however image image generation images llm management quality semantic text type world