Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation
This work addresses the problem of generating high-quality images from text for applications in AI and creative industries, representing an incremental improvement over existing models.
The paper tackles the limitations of Imagen in text-to-image generation by proposing Swinv2-Imagen, which uses a Hierarchical Visual Transformer and Scene Graph to improve semantic learning and image quality, achieving superior performance on datasets like MSCOCO, CUB, and MM-CelebA-HQ compared to state-of-the-art methods.
Recently, diffusion models have been proven to perform remarkably well in text-to-image synthesis tasks in a number of studies, immediately presenting new study opportunities for image generation. Google's Imagen follows this research trend and outperforms DALLE2 as the best model for text-to-image generation. However, Imagen merely uses a T5 language model for text processing, which cannot ensure learning the semantic information of the text. Furthermore, the Efficient UNet leveraged by Imagen is not the best choice in image processing. To address these issues, we propose the Swinv2-Imagen, a novel text-to-image diffusion model based on a Hierarchical Visual Transformer and a Scene Graph incorporating a semantic layout. In the proposed model, the feature vectors of entities and relationships are extracted and involved in the diffusion model, effectively improving the quality of generated images. On top of that, we also introduce a Swin-Transformer-based UNet architecture, called Swinv2-Unet, which can address the problems stemming from the CNN convolution operations. Extensive experiments are conducted to evaluate the performance of the proposed model by using three real-world datasets, i.e., MSCOCO, CUB and MM-CelebA-HQ. The experimental results show that the proposed Swinv2-Imagen model outperforms several popular state-of-the-art methods.