Conceptual Photography

<p>After much training and reviewing I present: good robot. This probably has the most adherence to prompts, best seed variety and most of all has a style that carried through from the dataset, while being different enough to present as a new thing. It is also the best out of all my krea loras to do facial expressions. It is trained just enough. You can run it at 1 or whatever strength you want. SAMEFACE is also reduced, as well as the extreme yellow tones of some previous loras. See images for what it can do or use it in your own prompts. This will probably be the last Krea2 lora from this dataset, I believe ive taken it as far as krea2 can take it. I may post a refinement of dirty pastel as there's a really good one in a 'polish' run i continued from that one, but who knows.</p>

good-robot.safetensors

(good robot[kr2])

(ghost v3[kr2])

(electrostatic[kr2])

(evil robot 2[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: 8c88c4f3e20e58d777635eba3caa5f412e56438f50c39296827fe5a1ef8a0b02