These models are merges and extractions of LoRa's that I made for my personal use and to try to correct some oversaturation and plastic skin issues generated by the Lightning LoRa's Lightning LoRa's from Lightx2v.
Description
I extracted a rank-4 LoRA from the QIE 2511 Lightning and merged it with the QI 2512 Lightning LoRA.
Models used in this merge:
https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning
https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning
FAQ
Comments (8)
Is this a Korean swearing ( 西巴 씨발) emoji?
I didn't understand
How does this work? Is there a trigger word for it? Is it supposed to swap face expressions?
No trigger word is needed, it's not just for swap, I made the swap example because it's the editing-related thing I've been working with the most lately, this lora is meant to be used in place of the official lightning lora from lightx2v, it was created from the official loras.
@NRDX maybe I'm fine sorry but how do you use it? What does it do? Can you give me some examples?
@simphirothpatreondrive684 Just look up what a lightning LoRA is, this isn't a new concept.
It's frikkin' lightning model, what part of lightning lora you don't get, lol :D
Can you share your ComfyUI merging workflow, I would like to try it with QIE 2509, thanks.





