Taiyi-Diffusion-XL is an open-source text-to-image generation model based on the Stable Diffusion framework, supporting both English and Chinese text-to-image generation. It represents a significant advancement over previous Chinese text-to-image models. The model can generate photo-realistic images based on textual descriptions, supports various image styles, and boasts high quality and diversity in generated images. It adopts an innovative training approach, extends vocabulary and position encoding to support long texts and Chinese, and is trained on large-scale bilingual datasets, ensuring its robust English and Chinese generation capabilities.