LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation
Open Access
- 26 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 643-654
Abstract
In the text-to-image generation field, recent remarkable progress in Stable Diffusion makes it possible to generate rich kinds of novel photorealistic images. However, current models still face misalignment issues (e.g., problematic spatial relation understanding and numeration failure) in complex natural scenes, which impedes the high-faithfulness text-to-image generation. Although recent efforts have been made to improve controllability by giving fine-grained guidance (e.g., sketch and scribbles), this issue has not been fundamentally tackled since users have to provide such guidance information manually. In this work, we strive to synthesize high-fidelity images that are semantically aligned with a given textual prompt without any guidance. Toward this end, we propose a coarse-to-fine paradigm to achieve layout planning and image generation. Concretely, we first generate the coarse-grained layout conditioned on a given textual prompt via in-context learning based on Large Language Models. Afterward, we propose a fine-grained object-interaction diffusion method to synthesize high-faithfulness images conditioned on the prompt and the automatically generated layout. Extensive experiments demonstrate that our proposed method outperforms the state-of-the-art models in terms of layout and image generation. Our code and settings are available at https://layoutllm-t2i.github.io/.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity2022
- Constrained Graphic Layout Generation via Latent Optimization2021
- LayoutTransformer: Layout Generation and Completion with Self-attention2021
- Visual-Relation Conscious Image Generation from Structured-Text2020
- Image Synthesis From Reconfigurable Layout and Style2019
- Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis2018
- AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks2018
- Image Generation from Scene Graphs2018
- StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015