<h2 id="rdbt-anima">RDBT [Anima]</h2>Finetuned + distilled.I use it as a clean starting point to stack more style LoRAs.See <a target="_blank" rel="ugc" href="https://civarchive.com/articles/30582">this page</a> for update log.For advanced users: The RDBT model is trained as LoRA natively. See <a target="_blank" rel="ugc" href="https://civarchive.com/models/2364703">this page</a> for original LoRA, update more frequently.This model is based on:<ul><li>prefix with ym: AnimaYume (<a target="_blank" rel="ugc" href="https://huggingface.co/duongve/AnimaYume">hf link</a>) (<a target="_blank" rel="ugc" href="https://civarchive.com/models/2385278">civitai link</a>). Has latest dataset, 1536px training. Check it's model page for more info.</li><li>prefix with b,p: Anima pretrained (<a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima">hf link</a>)</li></ul><hr />Sharing merges using this model is not allowed. If someone is selling this model as their own, I'm happy to list them here so everyone knows.Known model thieves: <a target="_blank" rel="ugc" href="https://tensorhub.art/u/613019935106639991">NukeA.I</a> (behind paywall on tensorart).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".<hr /><h3 id="usage:">Usage:</h3>Settings:CFG scale: 1~3. This model has been guidance distilled. You can disable CFG (CFG 1) and run the model 2x faster. Cover images are without CFG for demonstration.Steps: 16~24. (This is NOT a "turbo model", low steps is not supported and image will not be fully denoised. Add 0.5x turbo LoRA if you need 8 steps)PromptAlways specify style, or use a style LoRA. Otherwise, you will get random/mixed style.This is a feature, not a bug. This model does not provide a overfitted default style. Still highly creative. I use it as a clean starting point to stack more style LoRAs. I can stack whatever I want and get exactly what I stacked.Quality tags:It's recommended to omit all the quality tags, or just keep the "masterpiece", if you're not confident. Omitting those redundant tokens allows LLM to pay more attention on other words.Quality tags have been reinforced during distillation. Thus they don't have noticeable effects. Same as negative tags. If you use cfg, there is no need to dump "score_1, blurry, worst quality, jpeg artifacts, extra arms,... x100 words" in your negative prompt. Those things have been distilled out.<hr />Training settings~10k images finetuning -&gt; guidance distillationAll captions are NL from Google Gemini.Optimizer: adamw, constant lr 0.00002, weight decay 0.1, batch size 16.LoRA rank/alpha 24.Timesteps shift 3.Block 0-2 and adaln linear layers are skipped.

RDBT | Anima

rdbtAnima_ym1fV043.safetensors

ym1f v0.43

ym1f v0.43 [int8]

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: 99c17182db53beb60ce2a1ade41037bba4ff98a415e7cec16363ea4922987c73