(22/10/2026): v3.0 should be the final version for Anima. Next: MOSS Image <s>(aka. The greatest anime model that has ever been released.)</s>. <a target="_blank" rel="ugc" href="https://civarchive.com/models/3007506/rdbt-or-moss">Here</a>.<hr /><h2 id="rdbt-anima">RDBT [Anima]</h2>A general finetuned model, from a personal all-in-one dataset, mainly for digital art and drawings, focusing on lighting and textures, from wallpaper level digital art to 5-min sketch.Dataset contains ~10k images, handpicked by <s>professional</s> amateur artists. The criteria for evaluation are not visual appeal, but the drawing technique and the level of completion.Images are captioned by LLM. There is no trigger words or style tags. I'm too lazy to classify them. (TBH, most of the style can't be classified in just few words. It's hard to describe art.). So I used dynamic high caption drop rate hoping the model can guide itself from it's high noise steps.Some cover images look ridiculous; they're just for demonstration purposes for corner cases.Update log and version info: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/30582">link</a>.Useful links:<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2795449/rdbt-or-digital-art">RDBT | Digital Art</a>: My merged 16-step ckpt optimized for digital anime art. 4x faster. Easy to prompt.</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2364703/rdbt-or-anima-lora">RDBT | Original LoRA</a>: LoRA files for advanced users.</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2967964/16-step-acc-lora-or-anima">16-step Acc LoRA</a>: Style friendly, less AI slop, compared to the official Turbo.</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2874808/rdbt-or-160ke6-furry">RDBT | 160KE6 Furry</a>: Based on <a target="_blank" rel="ugc" href="https://civarchive.com/models/2700827">160kE6Anima</a> by @<a target="_blank" rel="ugc" href="https://huggingface.co/garaggge">garaggge</a>. 160kE6Anima "was trained on around 160k images from e621". It has extended knowledge and 3k+ style tags. Check its model page above for more info (list of styles, etc.).</li></ul><hr />Settings:<ul><li>Base version: CFG 4 and steps 24+. Euler.</li><li><s>Distilled version</s> (8s, 16s, discontinued): CFG: 1. Steps: 8 or 16. Euler.</li></ul>Prompt:Always specify @style in prompt, or use a style LoRA. Otherwise, you will get random/mixed style.Quality tags:You don't need quality tags. The fine-tuning dataset has higher quality than "masterpiece". Thus quality tags don't have effects. Omitting those redundant tokens allows LLM to pay more attention on other words.<hr /><h3 id="sharing-merges-using-this-model-is-not-allowed.">Sharing merges using this model is not allowed.</h3>This mode is a free and it will always be free. This "restriction" won't affect anyone. It's only aimed at those who steal others' models to sell.Known model thieves: <a target="_blank" rel="ugc" href="https://tensorhub.art/u/613019935106639991">NukeA.I</a> (selling this model behind paywall on tensorart).Because he is such a jerk I wrote a <a target="_blank" rel="ugc" href="https://civarchive.com/articles/31410/dev-story-rdbt-2">story</a> about it. Also contains a guide for trainers about "how to bake special trigger word into your model".

RDBT | Anima

rdbt_v2.3_animayume1.5_ckpt_int8convrot.safetensors

rdbt_v2.3_animayume1.5_ckpt.safetensors

ym1.5 v2.3 base

v3.0 base sma

v2.3 16s

b1 v2.3

v2.3 base

ym1f v2 base

v2 base

v2 16s

v1.2 4s

v1.2 16s

b1 v1.1

v1.0 16s

v1.0 8s

ym1f v0.43 [int8]

ym1f v0.43

b1 v0.39.b

ym0.5 v0.39

b1 v0.37.1

b1 v0.35

b1 v0.32.b

p3 v0.32

p3 v0.29

p3 v0.27

p3 v0.25

v0.25

p3 v0.24f 4-step dmd2

p3 v0.24f dmd2 turbo

p3 v0.24f 16-step dmd2

p1 v0.20f cfg

p1 v0.19f cfg b

p1 v0.12f cfg

fp16 patch v1.2

fp16 patch

p1 fp8

Files with SHA256: f1da66880cdf640ac63d537d365ac3576625042bc6f440824f179ef7dd3fd021