RDBT | Anima
详情
下载文件 (1)
模型描述
RDBT [Anima]
Finetuned + distilled. Higher aesthetic, stable, no overfitted default AI style, still creative and diverse, 3x faster, and probably has better prompt adherence, because of NL captions.
I use it as a clean starting point to stack more style LoRAs.
See this page for update log.
For advanced users: The RDBT model is trained as LoRA natively. See this page for original LoRA, update more frequently.
This model is based on:
prefix with ym: AnimaYume (hf link) (civitai link). Has latest dataset, 1536px training. Check it's model page for more info.
prefix with b,p: Anima pretrained (hf link)
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: NukeA.I (behind paywall on tensorart).
I wrote a story about it. Also contains a guide for trainers about "how to bake special trigger word into your model".
Usage:
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.
Prompt
Always specify style, or use a style LoRA. Otherwise, you will get random/mixed style. This model does not provide overfitted default shiny plastic glossy AI-slop style. This is a feature, not a bug.
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.
Training settings
~10k images finetuning -> guidance distillation
All 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.