Conceptual Photography

Took a break from generating for a long time but having fun training this model. Wow. So much better than Flux!Trained at 512px which after exhausting testing is the best resolution to capture the style, i have no idea why. Faces may be screwed up if small, use adetailer to fix. Use at lower values, like 0.8, or 1 if you're a risk-taker.

v8-dirty-pastel.safetensors

v8-(dirty pastel [kr2])

v7 - (infrared [f1])

v3.1 - (evil robot [f1])

v6 - (ghost [f1])

V2.1 - (angular v2 [f1])

v5.1 (junktopia v2[f1])

v5 (junktopia[f1])

v4 (monsterbeam[f1])

v3 (neon darkness[f1])

V2 (angular[f1])

V1 (love and wolves)

Files with SHA256: 7ff59a57bf6ab53a4134592d5188fd97dbe550e0cb4efaceeb60df048be9ea87