The LoRA model was created from 45 images taken from open sources on the Internet. LoRA was trained on the FLUX model. Sampling method Euler, CFG Scale: 3.5 experiment with values Steps: 14 - 28 experiment with values Weight: 0.3 - 1. Works well with weight: ( 0.5 - 0.8 ), experiment with weight up to 1.2
Description
The LoRA model was created from 40 images taken from public sources on the Internet. LoRA was trained on the FLUX modelSampling method DPM++2M SDE KarrasCFG scale: 2.5 - 3.5 experiment with valuesSteps: 14 - 28 experiment with valuesWeight: 0.3 - 1.Works well with weight: ( 0.5 - 0.8 ), experiment with weights up to 1.2
FAQ
Details
Downloads
939
Platform
SeaArt
Platform Status
Available
Created
10/10/2024
Updated
12/22/2024
Deleted
-
Trigger Words:
realism