This LoRA enhances Qwen-Image's support for Chinese, English, Korean, Japanese, Spanish, French, Portuguese, Russian, German, and Italian, making the generation effects of prompts more consistent. It's trained on the <a rel="ugc" href="https://modelscope.cn/datasets/DiffSynth-Studio/Qwen-Image-Self-Generated-Dataset">Qwen-Image-Self-Generated-Dataset</a>, which includes 1.5 million annotated multilingual prompts, with training code based on<a rel="ugc" href="https://github.com/modelscope/DiffSynth-Studio/tree/main"> DiffSynth-Studio</a>.The model is mirrored here for convenience.

Files with SHA256: 13ec8b51bb587290bb926bedeeadd94c6df145244c7854ad703c9ad442d989b3