
This lora was trained on 70 images from the artist 陽子 (@hrn_yc). A special shout out to flyx3 for making me aware of this artist. They also made a lora with this artist using Animagine XL V3 as the base, if you like this artstyle I recommend you give that one a try as well.
I wanted to see how this artstyle would look trained on Pony with my improved settings. I think it came out quite well. The hands are decent and the backgrounds are surprisingly decent as well.
To get the results you see in the images above, these are the settings I used.
Prompt: score_9, score_8_up, score_7_up ,score_6_up, source_anime, [your prompt] <lora:Faux_Retro_XL>
Negatives: mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry,simple background,
Sample: DPM++ 2S a
Steps: 33 (Whatever gives you the best results)
CFG Scale: 7
Highres Fix: 4xfoolhardyRemacri
Extension: [sd-webui-color-enhance] set to 0.5 (this increases the saturation a bit)
Even though this was trained on Pony, I exclusively use AutismMix and I recommend you do the same. All of the examples were made with that model.
描述:
训练词语:
名称: Faux_Retro_XL.safetensors
大小 (KB): 223101
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success