Trained on Base SDXL 1.0 Clip2
Note: Hires fix and/or Face Detailer highly recommended.
Started to experiment with SDXL, this is my first SDXL Lora upload after a couple of iterations, really loving the quality. I used a small dataset mainly for face. So rest of clothing didn't train properly. Could be improved.
Trigger: works without one. But if for some reason it doesn't you can use 3nid5
Strength: 0.9 - 1.1
Used ComfyUI, 8steps and EulerA+sgm_uniform. 2nd pass detailer+Facedetailer. SDXL lightning versions of JuggernautXL and epiCRealism.
ComfyUI users: If you want to know my generation settings, download a sample pic and drag it into your ComfyUI. It is my custom workflow for showcasing loras, and it makes sense for me, I don't have the patience to clean it up or make it understandable, so sorry in advance.
Trained on Base SDXL 1.0 Clip2
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
