Hi everyone overseas! ModelScope has launched its training service abroad.

My LoRa training is all done using ModelScope. Thanks to the ModelScope team for providing the training infrastructure. Give it a try!

https://www.modelscope.cn/aigc/modelTraining

Welcome everyone to use Lora of Qwen-Edit-2509 of Image Fusion, its performance is amazing！

Video tutorial:

YouTube：https://youtu.be/xhPDto-XgFs

Blibili：https://www.bilibili.com/video/BV178x5zJEcD/

Running online: https://www.runninghub.ai/model/public/1985634590226358274?inviteCode=rh-v1331

Trigger words:白底图转场景

You can add subject and scene description after the trigger word, for example: 白底图转场景,将图片中的汽车放在户外场景中（Meaning：Convert the white background image to a scene and place the car in the picture in an outdoor scene）

You also need this lora and use them together: https://huggingface.co/lightx2v/Qwen-Image-Lightning/tree/main