RDBT [Anima]

Personal finetuned model. I use it as a starting point to stack more style LoRAs.

See this page for update log. See this page for LoRA version.

All cover images are "raw" output, 1024px, no editing/upscale etc. Metadata included.

Sharing merges using this model is not allowed. It has special trigger words. There is no false positive. Known model thieves: NukeA.I (closed-weight on tensorart)

Usage:

Settings:

CFG scale: 1~4. This model has been guidance distilled for better quality. You can disable CFG (CFG 1) and run the model 2x faster. Cover images are without CFG for demonstration.

Prompt

Specific style is required! This model does not provide a default style. You should always prompt specific style. Or use a style LoRA. Otherwise, you will get random/mixed style. This is a feature, not a bug.

(v0.32+) There are some "roughly classified" trigger words, they are trained so they have effect, but they are not "specific style":

• @anime sketch: Low complexity. Rough outlines.

• @digital anime illustration: Typical "anime". Clear and fine outlines. General complexity.

• @digital art: More complex lighting, textures than typical "anime".

• @cinematic digital art: More lighting, postprocess effects, semi-realistic, etc. A little bit chaotic.

Quality tags:

It's recommended to omit all the quality tags, or just keep the "masterpiece". 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.

Omitting those redundant tokens also allows LLM to pay more attention on other words.

Training:

Anima pretrained base ckpt -> 5k general images finetuning -> 500 highest aesthetic images finetuning -> guidance distillation.

All captions are NL from Google Gemini.

Optimizer: adamw, constant lr 0.00002.

LoRA rank/alpha 24.

Guidance distillation target CFG 4.

Block 0-2 and adaln linear layers are skipped.