Pony Diffusion V6 Art Style - "AAM XL Screencap"

Version 4.0

Version 3.0

Version 2.0

"AAM XL Screencap Style" For Pony Diffusion V6

Last Update：2024-07-15 19:37:11

Pony Diffusion V6 Art Style - "AAM XL Screencap"

Reprint

Favorite Now & Sort Later

/upscale

score_9, score_8_up, score_7_up, source_anime, rating_safe, scenery, outdoors, sky, cloud, (no humans), star (sky), mountain, mountainous horizon, flower, starry sky, grass, landscape, shooting star, nature, tree, blue sky, sunset, cloudy sky, field, night, night sky, plant, hill, evening, cumulonimbus cloud, very aesthetic, absurdres, detailed background, <lora:ZootPonyAnime_V1_r2:0.8>

diffusionfanatic1173

Reprint

Favorite Now & Sort Later

/upscale

diffusionfanatic1173

Reprint

Favorite Now & Sort Later

/upscale

score_9, score_8_up, score_7_up, source_anime, rating_explicit, blonde-haired 1girl penetrated by 1boy, outdoors, winter, (2d), detailed background, <lora:ZootPonyAnime_V1_r2:0.7>

diffusionfanatic1173

Create

Favorite

Download

Model Source:

civitai

Type:

LORA

Base Model:

Pony

Tags:

#Anime#Style#art style#ArtStyle#styles#screencap#ponyxl#pony xl#pony style

Trigger Words:

source_anime

License Scope:

Creative License Scope

Online Image Generation

Merge

Allow Downloads

Commercial License Scope

Sale or Commercial Use of Generated Images

Resale of Models or Their Sale After Merging

Model Parameters:

Review:

Retrained against my Tweaked Base Pony XL checkpoint (to allow for some subtle quality improvements) on a dataset with around 200 more images than V3's. The whole dataset was also recaptioned from the ground up using the same combined "Florence 2 Large detailed captions + WD-VIT-3 Booru tags" approach I've been using elsewhere recently.

This version no longer uses a unique trigger, instead being trained directly against 'source_anime'. Using '2d' in the positive and '3d, cgi' in the negative will also tend to strengthen the effect. Recommended strength is around 0.7 - 0.8.

0 comment