<p><strong>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.</strong></p><p>The recommended resolution you can set:</p><p>1024*1024 / 1152*896/ 896*1152 /1216*832</p><p>832*1216/ 1344*768/ 768*1344 / 1536*640</p><p>640 * 1536</p><p><strong>Sampler: </strong>Euler a</p><p><strong>Step:</strong> 20~30</p><p><strong>CFG: </strong>5~7</p><p>Positive Prompt:</p><p>score_9, score_8_up, score_7_up,((source anime, best quality, best aesthetic, perfect anatomy, Art Composition, Gold Ratio)),{input what you want}</p><p>Nagative Prompt:</p><p>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],</p>