Type: LORA (FLUX)
Model introduction: A taekwondo hall with a strong sense of technology
Trigger word: WD
Number of iterations: 30
Weight 0.8
CFG 3.5
The material set uses: 512-768/768-512
Refining the bottom membrane: The basic model FLUX1-dev is recommended as the basic large model, (the general applicability of other models can be tested independently) Iteration steps Sampling steps: 30, Sampling method: Euler Size recommendation: can be tested independently, all training materials are 768*1024 Enhancement algorithm: 8G memory recommended: 4x-UltraSharp/R-ESRGAN 4x+ Friends with sufficient memory: 8x-NMKD-Superscale
Description
Details
Downloads
33
Platform
CivitAI
Platform Status
Available
Created
7/1/2025
Updated
9/30/2025
Deleted
-
Trigger Words:
WD
Files
FLUX科技感跆拳道馆-000019.safetensors
Mirrors
CivitAI (1 mirrors)
Other Platforms (TensorArt, SeaArt, etc.) (1 mirrors)