This LoRA is suitable for the Qwen Edit model
NEW!_Workflow:：https://www.runninghub.ai/post/1966557857586065410/?inviteCode=rh-v1172
Register for free use
保持一致性强度推荐：0.5-0.8 万物迁移强度推荐：1.2-1.6
Recommended consistency intensity: 0.5-0.8; recommended migration intensity of all things: 1.2-1.6
Maintain consistency in image modifications, remove grease, and keep the quality consistent with the original image. Increase the intensity of all functions!
Thank you for the feedback images and testing from friends. Acknowledging participants: wallen, zero, jiong, yunor
Trigger words: Put it here, maintain the light and shadow of the painting（It works better to use Chinese)：Put it here,保持画风光影不变
If you need commercial customization or any suggestions or help, please contact me
V:budabiaoa Q:123326400
Description
This LoRA is suitable for the Qwen Edit model
FAQ
Comments (19)
When I add this during upscaling, it works really well and perfectly. This is probably the best combination available locally right now.
Thank you for your support. There will be more optimized versions coming later. If you have any issues, feel free to bring them up to help me find the direction for optimization. Also, if you have good images, please share them to help me improve. Thank you.
This is fantastic! Works very well! Tahnkyou a lot
It's good as long as it's useful. If there's a chance, you can give more feedback images.
好用！！完美补足了qwen模型本身的不足！！！硬盘有点不够用了，感觉我的kontext可以进回收站了。这模型提示词没有kontext那么刁钻，还能用中文。。我太爱了。
哈哈kontext不着急删除。让子弹再飞一会儿。不过qwen的高清晰度还原和中文字的适配，的确让人爱不释手
It doesn't work for me, can you tell me which trigger word to write - Put it here? or should this word be written in Chinese? I placed the kitten and the dog on the couch and prescribed - Put it here, but for some reason the dog applied and the kitten did not, and the dog did not fit into the environment, can you tell me what I am doing wrong?
"put it here" currently being tested with Qwen Edit still has many aspects worth studying. You can also try to get different results by adjusting the LoRA strength. This version is also a test version. I don't know if it can be helpful to you. If you have new findings or shortcomings, you can leave a message for me. Help me get more information to update the next version. Thank you.
put here, "your prompt", seamless
带佬的lora补足了Qwen的一致性问题，就是有的时候有点太强了（狗头保命）对于现实的角色来说就是劲！霸！强！对于想要二次元转真实的角色的来说有个小小的问题就是有时候会直接生成原图（小声）其他的方面都是很好的了！
哈哈你可以尝试修改lora强度来解决一些事情。具体参数需要来测试。如果你觉得值得花这个功夫的话可以试下。。我的电脑太差。测试成本很高。如果有好的发现可以分享一下谢谢啦
@Futurlunatic 可以的~我正在做强度测试，等测试号我会发上来的，（我尽量选一些穿的厚实的,C站吞了我十几张图了）
@fangfei7005918 哈哈还会有新版本。。你是在群里吗 ？
@Futurlunatic 倒是没有。。我是在阿B那刷视频的时候看到有人分享你这个插件，就下来测试一哈子
@Futurlunatic 期待新版本啊
@koori 会有的。还需要大量的测试已经更新了几个版本还没有找到合适的参数
@fangfei7005918 谢谢你的关注和帮忙测试。有发现多反馈。谢谢啦
Just wanted to say thank you for including english translation!
Thank you very much for your support!