I use the training data totally about 980 pics on MooMooにじげん SD1.5 model start to training basic on Pony Diffusion V6.
The recommended resolution you can set:
1024*1024 / 1152*896/ 896*1152 /1216*832
832*1216/ 1344*768/ 768*1344 / 1536*640
640 * 1536
Sampler: Euler a
Step: 20~30
CFG: 5~7
Positive Prompt:
score_9, score_8_up, score_7_up,((source anime, best quality, best aesthetic, perfect anatomy, Art Composition, Gold Ratio)),{input what you want}
Nagative Prompt:
score_4,score_3,score_2,score_1,(worst quality, low quality:1.4),(mutated hands and fingers,one hand with more than 5 fingers, one hand with less than 5 fingers:1.3),uply,(logo,watermark,username:1.2),nsfw,lowres,(bad),text,error,fewer,extra,missing,worst quality,jpeg artifacts,low quality,unfinished,displeasing,oldest,early,chromatic aberration,signature,extra digits,artistic error,scan,[abstract],