please
#4
by igty - opened
Dear LightRx Team,
I am reaching out on behalf of a significant user base, including 6–8 Discord servers, the open-source community, and various content creators.
We are writing to urgently request an 8-step LoRA compatible with Qwen 2512. Currently, the available 4-step LoRA produces quality that is insufficient for Text-to-Image generation. While the 4-step version performs adequately for image editing, it creates unusable results for text-to-image workflows.
The community heavily relied on the high-quality 8-step LoRA provided for previous versions. We would greatly appreciate it if you could release a similar 8-step solution for the current model.
Thank you for listening to community feedback.
they didnt listen
OK, we are training it.
yeeee