Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗
Train based on AnyLora model. Training materials are basically official arts and fanarts.
Modellquelle
Quellenbeschreibung
Train based on AnyLora model. Training materials are basically official arts and fanarts.
Strongly recommend weights from 0.6 to 0.8(and the blocked ver from 0.8 to 1.0 maybe),and enable hires.fix.
Training used lora block weights to set the pose free, you may also use your own blocks ;
If you find any problem when using the blocked ver,try switch to the noblocks ver and use the following Lora block weights:
1,1,1,1,1,0.5,0.5,0.1,0.86,1,1,1,1,1,1,1,1
You may use the following prompts to generate this character:
Basic characteristics:
Quellen
1 QuelleModellartefakte
1 ArtefaktShadowverseTechnolordV2blocked.safetensors
safetensors · 58,2 MB · SHA-256 e5c5b9cdc0af…09a8 · Civitai
HerunterladenQuellenauszüge
1 AuszugSource context: 366 downloads · Type LoCon · Base model SD 1.5
Blonde hair,(very long hair),(glowing)blue/purple eyes,mecha musume;
Default costume:
Hair ornament(horns),wide sleeves,white dress,mechanical arms,parts,joints,(armor);
Extra elements:
Electricity,magic,floating object,magic,ring;
Mecha form:
Mechaform,robot,(no humans);
