<h3 id="hassaku-anima">Hassaku Anima</h3><hr />Join my <a target="_blank" rel="ugc" href="https://discord.gg/zSR5FcYWWE">Discord</a> for everything related to anime models and AI art. If you’d like to support my work, you can do so on <a target="_new" rel="ugc" href="https://subscribestar.adult/citrus-models">SubscribeStar</a> Every bit helps me continue making AI models and even an AI VTuber, which is currently in the works. <hr /><h3 id="how-to-use">How to Use</h3>You need to use ComfyUI or Forge Neo. 20-50 steps, CFG 3-6, (i like to use 25 stepts with cfg of 3.5 and er-sde as sampler). - Put @ in front of artist tags - Use lowercase for tags and spaces instead of underscores. - Recommended positive: "masterpiece, best quality, score_7", but since masterpiece is altered, in some cases masterpiece is enough - Recommended negative: worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts" - When using a tag that is different between Danbooru and Gelbooru, prefer the Gelbooru version. <hr /><h3 id="supporters">Supporters</h3>Special thanks to my supporters: Estryark, SETI, Kodokuna and dataset captioners mariotheknight and tamashiicolle <hr /><h3 id="recommended-resolutions-for-anima">Recommended Resolutions for Anima</h3>Here are some resolution suggestions for Anima:<ul><li>1536 × 640</li><li>1344 × 768</li><li>1216 × 832</li><li>1152 × 896</li><li>1024 × 1024</li><li>896 × 1152</li><li>832 × 1216 — most recommended</li><li>768 × 1344</li><li>640 × 1536</li></ul>Larger resolutions are possible. Note: It is a Diffusion Transformer (DiT) model, it is less restrictive on sizes in compare to a Unet like Illustrious, you can use bigger resolutions.<hr /><h3 id="version-and-license-info">Version and License Info</h3>V0.1: A small-scale style training test, intended to see how adaptive Anima is. V1: Test for character training with nte characters and femme soule (pukey goddess shot trick). Better use of the style training set. V1 Style: Focus on a consistend style. Revert training of nte characters and femme soule (pukey goddess shot trick), because of forgetting issues of anima itself. License: <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.md">Anima</a>

Hassaku (Anima)

Every training was done with NL and tags, but only for style purposes. Tested with my settings: 22 to 28 steps, CFG 3.5 to 4, er_sde, no artist tags and minimal quality tags. Better:<ul><li>Better background compositions, less random, more structured</li><li>Fewer "melted-looking" elements</li></ul> Slightly better (in around 1–2 out of 5 images):<ul><li>Better hands</li><li>Fewer random light particles</li></ul> Better or worse depending on taste:<ul><li>Faces and bodies are more in shadows</li><li>It tends to produce fewer simple "dot noses" </li></ul>Note: No additional knowledge was trained into the model, as Anima have severe knowledge loss across concepts when trained for extended periods without datacenter-level hardware, which I do not have.

Files with SHA256: 4162de48c68fdd73ee673e512011a02e90d5eb2059756cf12a6f5907c8475b7f