{"id":649,"date":"2025-08-26T05:44:13","date_gmt":"2025-08-26T05:44:13","guid":{"rendered":"https:\/\/pixai.art\/articles\/?p=649"},"modified":"2025-12-16T12:51:56","modified_gmt":"2025-12-16T12:51:56","slug":"dit-lora-training-guide-pixais-new-multi-version-support-and-dataset-reuse-features","status":"publish","type":"post","link":"https:\/\/pixai.art\/articles\/en\/dit-lora-training-guide-pixais-new-multi-version-support-and-dataset-reuse-features\/","title":{"rendered":"DiT LoRA Training Guide: PixAI’s New Multi-Version Support and Dataset Reuse Features"},"content":{"rendered":"\n

The PixAI community has been eagerly awaiting enhanced LoRA support for DiT models, and it’s finally here! \ud83c\udf89 This guide will walk you through all the new features, including multi-version LoRA support<\/strong>, cost-saving dataset reuse<\/strong>, and best practices for DiT LoRA training<\/strong>.<\/p>\n\n\n\n

\ud83d\ude80 Full DiTLoRA Support<\/strong><\/h2>\n\n\n\n

You can now seamlessly use and train LoRAs on DiT-based models, including the popular Tsubaki<\/a> and Serin<\/a> models. This opens up entirely new creative possibilities for your AI art generation.<\/p>\n\n\n\n

Start training<\/a><\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\ud83d\udd04 Multi-Version LoRA System<\/strong><\/h2>\n\n\n\n

LoRAs on PixAI now support multiple versions<\/strong> under the same model card. That means instead of uploading a whole new model each time, you can manage multiple versions of your LoRA in one place. The multi-version support allows you to create new versions of existing LoRAs for different base models.<\/p>\n\n\n\n

    \n
  1. To add a new version, open your model\u2019s detail page by clicking on the model, then select the icon in the top-right corner<\/strong>.<\/li>\n<\/ol>\n\n\n\n
    \"\"<\/figure>\n\n\n\n
    \n
    \n

    <\/p>\n\n\n\n

    2. On the detail page, click Add version<\/strong>.<\/p>\n<\/div>\n\n\n\n

    \n
    \"\"<\/figure>\n<\/div>\n<\/div>\n\n\n\n

    3. You\u2019ll be redirected to the LoRA training page, and once training is complete, the new version will be automatically added under the existing model.<\/p>\n\n\n\n

    \"\"<\/figure>\n\n\n\n

    Switching Versions:<\/strong><\/p>\n\n\n\n