Hassaku aims to be an anime model with a bright, distinct, slightly 2.5D anime style. 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: pttcot, 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

A small scale style finetune of anima, it was initially not meant to be released and was only a internal test. The training worked better than expected. I like the result so that I decided to release it. The model received style-set training focused on the tag "masterpiece". Only about 1/4 of the dataset included NL, using a mix of tags and natural language. Thanks to @mariotheknight and @tamashiicolle for helping me in captioning the datasets! Those sets was originally intended for KLEIN fine-tuning, but that experiment ended up failing over the course of 3months. The fine-tune target is Anima Base v1.0. Since this is not a style LoRA merge, but a model natively trained with a style, tags like traditional media, watercolor or @artist styles should still work normally without change. Test Notes for V0.1 The learning rate was too high, so around 1 in 10 images may show more noticeable limb issues or color bleeding. However, the overall base style in use with masterpiece looks better and closer to models like Illustrious, which was the intended direction. Disclaimer: Since this is not a forced LoRA-style merge, the style will vary, especially when generating characters.

Files with SHA256: 4d2f4978c7823493be13cd10af0d18ebc1535540ae3117fa2c818154b927f20e