HunyuanDiT-v1.1 is a multi-resolution diffusion transformer model developed by the Tencent Hunyuan team. It has excellent Chinese and English understanding capabilities. The model realizes data iterative optimization by combining a meticulously designed transformer architecture, text encoder, and positional encoding, along with a fully constructed data pipeline from scratch. HunyuanDiT-v1.1 can conduct multi-round multi-modal dialogues and generate and refine images based on context. After comprehensive evaluation by over 50 professional human evaluators, HunyuanDiT-v1.1 has achieved new state-of-the-art results in Chinese-to-image generation compared to other open-source models.