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.転載モデルは学習・共有目的のみで使用し、著作権は原作者に帰属します
2.モデルの認証は公式チャンネルでご連絡ください。クリエイターの権利保護に努めています クリックして認証
