VAUXZ ANIME MERGE
This model was merged to create a model that could generate:
crisp details
high contrast
good dark vibes
great lighting and depth
Male characters as good as it does female characters
great 832 x 1216 anime images
Model was merged with my loras
PONY Recommended settings
Sampler: Euler a - Karras
Resolution: 832 x 1216, 1024 x 1024
CFG: 7
Illustrious Recommended settings
Sampler: Euler a - Karras/SGM Uniform
Resolution: 832 x 1216, 1024 x 1024
CFG: 5.5
XL Recommended settings
Sampler: DPM++ 2M SDE - Karras
Resolution: 832 x 1216, 1024 x 1024
CFG: 6.5
Quality tags:
Pony
score_9, score_8_up, score_7_up, (masterpiece:1.2), (best quality:1.3)Illustrious
(masterpiece), (best quality), masterwork, semi-realisticNegative prompt:
Pony
low quality, score_6_down, score_5_down, score_4_down, score_3_down, score_2_down, score_1, NEGATIVE_HANDSIllustrious
low quality, 2koma, 4koma, signature, watermark, bad ???????, jpeg artifacts, signature, watermarkPositive lighting tags:
low-key lighting, lo-fi, glow, dynamic cinematic lighting, ray_tracing, global illuminationNegative lighting prompts:
bright, spotlight, front lit, camera flashI am not sure how those tags should affect the image. lol they are just what I use.
Optional: ADetailer for face details
Description
This will probably be the new base version for the upcoming updates.
better details
better depth and lighting
more refined pony prompt adherence
Finer outlines
more polished output
should be more versatile
Better anatomy
Better textures?
Better Pony LoRa compatibility
doesn't lean too much on the color green
Still the same settings:
Sampler: Euler a - Karras
Resolution: 832 x 1216, 1024 x 1024
CFG: 7