Conceptual Photography

START BELOW 0.7, 0.5-0.65 IS THE SWEET SPOT. You can go up to 0.8 or so if the subjects are close to the camera, i've also gotten good results at that level too but you risk mutations going that high. This is more experimental than the others. IT ADDS A LOT OF DETAIL, to reduce this use the fantastic detail slider here at negative values (-6 is good): <a target="_blank" rel="ugc" href="https://civitai.red/models/2772451/detail-slider-krea-2-loraholic?modelVersionId=3121642">https://civitai.com/models/2772451/detail-slider-krea-2-loraholic?modelVersionId=3121642</a>Beautiful, scary, unique. Good at multiple subjects (like the original Evil Robot was supposed to be).Just look at the pictures to see if its your jam. It is GREAT for mixing with other loras to force a different composition and style. Trained with prodigy on extra high settings.I have a Good Robot coming very soon too, something thats better than the default model at multiple characters, but is cleaner.

evil-robot-2.safetensors

(evil robot 2[kr2])

(ghost v3[kr2])

(good robot[kr2])

(electrostatic[kr2])

(ghost v2[kr2])

(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: dae3a86b34337fe7ee738dec7ad07c5e006f2e3a49818a0d022100458a842b23