this is a finetune for anime style with stable cascade (stage_c lite)my goal is to make similar style to counterfeit and darksushi for stable cascadefor training i followed <a target="_blank" rel="ugc" href="https://github.com/2kpr/StableCascade">this</a> from github0.1:i traned for 5k steps with ~300 images from <a target="_blank" rel="ugc" href="https://civarchive.com/models/4468/counterfeit-v30">counterfeit</a> then i trained another 5k steps with ~350 images from custom merge model that i made a while agov0.2:trained with more images ~750recommended for better quality: use compression=32negative:low quality, realistic - sometimes it makes the image worse, sometimes it helpsbad anatomy, deformed - generally helpspositive: i've posted the prompt template used when training in trigger words, but you can try whatever prompt you want (duh)nsfw: please don't try to generate nsfw, i trained with ~100 nsfw images but it looks bad, i'll add more in the futurev0.3:retrained from scratchmy experimental settings so far:cfg: 2-2.5 seems good5 steps for stage_b, 10 if you want a bit more detailnegative:<pre><code>cartoon, closeup, lowres, simple background, artifacts, (realism, blurred:1.2)</code></pre>(should be better than nothing, but feel free to test with other negatives)cartoon in negative seems to add more detail to the image4k, masterpiece, high quality doesn't make the image bettercompression=42 is goodif you want the character to look more manly, put 1girl, girl in negative, it could helpretrained:&gt;1k 1024x1024 for 15k steps650 1024x1792 for 7k steps328 1536x1024 for 5k steps129 1024x1280 for 2.5k steps (which are 768x when training)so the model can generate images with different sizes,my idea with the last one is that when characters occupy a relatively small portion of the overall image or appear at a distance the model will know how to generate them (cause it's seen how to make characters in small portions of pixels), dunno if it actually works

CounterSushi - Stable Cascade

v0.2 - trained with more images ~750recommended for better quality: use compression=32negative: low quality, realistic - sometimes it makes the image worse, sometimes it helpsbad anatomy, deformed - generally helpspositive: i've posted the prompt template used when training in trigger wordsbut you can try whatever prompt you want (duh)nsfw:please don't try to generate nsfw, i trained with ~100 nsfw images but it looks bad, i'll add more in the future

Files with SHA256: 4e65b42a811c81ac2bfa4cc40b167e52a8ec6d10ba9bcf98225a96e7f1cfebfd