aaaautismPonyFinetune_v35

Prompt
score_9, score_8_up, score_7_up, BREAK 1girl, upper body, facial tattoo, dog, cat, brown eyes, german shepherd, long hair, japanese flag, black eyes, chin strap, samus aran, tattoo, copyright name, border, goggles, manga cover, white border, tassel, chest jewel, bodysuit, mask, black hair, shiba inu, looking at viewer, artist name, hime cut, blunt bangs, animal hug, black cape, pink flower, parted lips, black bodysuit, goggles on head, blue background, straight hair, flower, kimono, sidelocks, mouth mask, red flower, brown kimono, expressionless, forehead tattoo, brown hair, cape, dog mask

Negative Prompt
greyscale, monochrome, realistic

Prompt
score_9, score_8_up, score_7_up, BREAK tousen, 1girl, gothic dress, frills, brown theme, fingernails, blood, spiked headband, holding heart, monster girl, frown, hair between eyes, frilled sleeves, neck ribbon, black background, corset, teeth, winged arms, grin, holding, sharp teeth, vampire, eyelashes, bob cut, short hair, smile, dress, heart, ribbon, blood splatter, goth fashion, nail, wavy hair, evil smile, bat wings, looking at viewer, wings, blood from eyes, spot color, long fingernails, long sleeves

Negative Prompt
greyscale, monochrome

Model description

(AAA)Autism

v3.5 note: Direct continuation of v3. Same amount of training done, but at finer values, and with better technique that im slowly moving from other trainer. Should fix some stuff, and be more compatibe with loras.

v3 note: different, less unstable training. Should have less issue than v2, or alternative v3(which i wont release, it's fucked, lol, and i deleted it). Creates bigger difference from ancestor, while being trained for less steps overall.

v2 note: it is experimental af. You might notice issues, and possibly worsening on some components. Or you might not. You might find it better. This is further merge of experimental training. Use v1, if you find it worse.

Finetune of PonyDiffusion v6 based on Anzhc's Anime Aesthetics dataset, and transferred to AutismMix.

Goal is to bring less 3D anime style through native means(i.e. direct finetune), that lots of us are used to from 1.5 models derived from NAI, a bit closer, but keep Pony knowledge and loras compatibility intact, if possible.

Kofi - https://ko-fi.com/anzhc

This is mostly an experimentap piece that is used to lay down basic grounds for finetune of higher magnitude.

Brightness tagging (extremely dark, very dark, dark, bright, very bright, extremely bright) was used, but tags did not learn anything of use. Balanced iamges were not tagged.

Rest of details are yet to be disclosed.

Overall, i really wished for it to be more capable with abstract compositions.

Example of change: