<h3 id="rdbt-anima">RDBT [Anima]</h3>Distilled model (aka. "turbo"). It delivers faster speed and higher aesthetics with only 12 NFEs, 5x faster than base model (60 NFEs).Based on <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima/tree/main/split_files/diffusion_models">pretrained anima (hf link)</a>.See <a target="_blank" rel="ugc" href="https://civarchive.com/models/2356447">this page</a> for how to use the model.Sharing merges using this model is not allowed.Random experiment, random quality. New version != better version. Feel free to leave feedback.<hr /><h3 id="update-log">Update log</h3>(4/29/2026) p3 v0.29.b: Further trained <a target="_blank" rel="ugc" href="https://civarchive.com/models/2356447?modelVersionId=2905630">v0.29</a>.====== alpha testing ========<code>[base model version] [finetuned model version] [distillation method] [distillation version]</code>f = finetuned, cfg = cfg distilled, dmd2 = <a target="_blank" rel="ugc" href="https://arxiv.org/abs/2405.14867">distribution matching distillation</a>.N-step dmd2: N means the model can output an image without noise after N steps. It's not a mandatory fixed setting. It's a lower limit. You can always use &gt;N steps. Lower N = stronger distillation.(4/14/2026) p3 v0.24f dmd2 b: Comparing with "v0.24f dmd2": Images should be sharper.(4/11/2026) p3 v0.24f cfg b: Improved stability and diversity, comparing with previous 0.24f cfg.(4/10/2026) p3 v0.24f dmd2: roughly 12~16 steps distillation. This is intentional. Low steps distillation = ai slop style without complex texture.(4/8/2026) p3 v0.24f cfg: Rebased on preview3. Finetuned base model has -40% steps than v0.23. Less overfitted (?).(4/4/2026) p2 v0.23f dmd2 b: Different distillation settings. Almost a 4 steps dmd2. Maximum stability.(4/4/2026) p2 v0.23f dmd2: 8 steps dmd2. First dmd2 anima (?).(3/28/2026) p2 v0.23f cfg: Rebased on preview2. Distillation: improved small details and stability (removed a regularization in distillation target and changed to second-order method).Voting result: v0.20fd won. Thanks for the feedbacks.(3/24/2026) preview1 v0.20f cfg b: Distillation: Different settings optimized for anime, high contrast and saturation.(3/23/2026) p1 v0.20f cfg: Dataset: More furry. Finetuned base model: from v0.12 + more 100% steps. Distillation: Fixed noisy pixels this time, really.(3/14/2026) preview v0.19f cfg b:Updated dataset. Some private datasets have been dropped. You might notice the style changed.<s>Fixed high-freq artifacts in v0.12, now you should get a clear image without noisy pixels</s>b: Testing new distillation settings. Higher contrast. Aligned with common anime art.(2/19/2026) preview v0.12f cfg:Better stability and details, extended dataset.(3/8/2026) preview v0.11f cfg 512px:Prove of concept version for v0.12. Same dataset and settings as v0.12, except it was trained with 512px res.Released by request, as it might be very useful. Running model in 512px and cfg1 is extremely fast (x10 faster, e.g. 30s -&gt; 3s). If you don't have a beefy GPU. You can use this version to test your ideas/prompts in few seconds.(2/12/2026) preview v0.6 cfg:CFG distilled only. No finetuning. Cover images are using <a target="_blank" rel="ugc" href="https://civarchive.com/models/2385278">Animeyume v0.1</a>.(2/3/2026) preview v0.2f cfg:Speedrun attempt, mainly for testing the training script. Limited training dataset. Only covered "1 person" images plus a little bit of "furry". But it works, and way better than what I expected.

RDBT - Anima

anima_preview_rdbt_v0.6_cfg_distilled_only.safetensors

p1 v0.6 cfg

p3 v0.29.b

p3 v0.24f dmd2 b

p3 v0.24f cfg b

p3 v0.24f dmd2

p3 v0.24f cfg

p2 v0.23f dmd2 b

p2 v0.23f dmd2

p2 v0.23f cfg

p1 v0.20f cfg b

p1 v0.20f cfg

p1 v0.19f cfg b

p1 v0.11f cfg 512px

p1 v0.12f cfg

p1 v0.2f cfg

Files with SHA256: 5f0db5943ccf4b3328005ded583b779df5b011e78edfdb1308e22244a4840696