A bit of an expirment to se how it goes and get a bit more face variation than the normal Qwen.
Contains part of lightx2v_Qwen-Image-Lightning-4step-8step-Merge plus 2 self trained Loras
Use 10-16 steps, CFG 1 (you can use 2 or 2.5 but sometimes it feels to saturated).
I mostly use Euler beta or kl_optimal.
Description
Details
Downloads
27
Platform
SeaArt
Platform Status
Available
Created
8/16/2025
Updated
8/16/2025
Deleted
-
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.