








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
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
