Conceptual Photography

<p>V6 - GHOST</p><p>This one is the one out of all the trainings that I feel is one of the 'truest' to my personal photography style--so far. More desaturated colors, gritty texture, bounce-flash, tighter shots, lots of variations in angles(relative to default flux). It is slightly overtrained in that regard but it still has prompt adherence--it may just do it's own thing every once in a while--but will still for the most part be true to what is put in the prompt. It still has SEED variety and creativity but may need adetailer to fix faces and/or have sameface since dataset is only 100 images. I personally use Huen/Beta for these since it gives a more textured/gritty feel to the images which I think works well for the style--but Euler/Simple will also work (Huen/Beta will add to generation times considerably). Best settings-- 5 CFG, 896x1344, Huen/Beta. Trained at 96 dim and 128 alpha.</p>

concept_photography_v6_ghost.safetensors

v6 - (ghost)

v7 - (infrared)

v3.1 - (evil robot)

V2.1 - (angular v2)

v5.1 (junktopia v2)

v5 (junktopia)

v4 (monsterbeam)

v3 (neon darkness)

V2 (angular)

V1 (love and wolves)

Files with SHA256: 84ea34fbd09acebfb787e7e559262dc4e8d57326a5f59d1fc7a6de6d7c3b371b