We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images. Finally, Hunyuan-DiT can perform multi-turn multimodal dialogue with users, generating and refining images according to the context. Through our holistic human evaluation protocol with more than 50 professional human evaluators, Hunyuan-DiT sets a new state-of-the-art in Chinese-to-image generation compared with other open-source models. Code and pretrained models are publicly available at github.com/Tencent/HunyuanDiT

翻译：我们提出了Hunyuan-DiT，一种对英文和中文均具有细粒度理解能力的文生图扩散Transformer。为构建Hunyuan-DiT，我们精心设计了Transformer结构、文本编码器和位置编码；并从头构建了完整的数据流水线，用于迭代模型优化的数据更新与评估。针对细粒度语言理解，我们训练了一个多模态大语言模型来优化图像标注。最终，Hunyuan-DiT能与用户进行多轮多模态对话，根据上下文生成和优化图像。通过由50余名专业人类评估员参与的全方位人工评估协议，Hunyuan-DiT在中文图像生成任务上相较其他开源模型达到了新的最优水平。代码与预训练模型已开源至github.com/Tencent/HunyuanDiT。