Raejin Anima
Overview
Raejin Anima is a specialized fine-tune of the Anima base model, meticulously crafted to elevate its visual fidelity. This model addresses specific limitations found in the original, aiming to deliver a more polished, aesthetic, and balanced output while preserving the core strengths of the base model.
Model Details
- Developed by: Raelina
- Model type: Diffusion-based text-to-image generative model
- Finetuned from: Anima
- Prompt style: Booru-style tags and Natural Language
Training Details
v0.1 (Experimental Alpha)
- Base Model: anima-preview2
- Method: Full fine-tuning using the kohya/sd-scripts trainer.
- Stability: LLM Adapter was disabled during training to mitigate catastrophic forgetting, ensuring the model retains its foundational knowledge while adopting new stylistic improvements.
- Dataset: Trained on a curated set of 2,2k high-quality images, utilizing a hybrid captioning strategy of both booru-style tags and natural language to enhance prompt adherence and stylistic depth.
Recommended settings
- Positive prompts:
masterpiece, best quality, absurdres
- Negative prompts:
low quality, worst quality, jpeg artifacts, bad anatomy, bad hands, bad proportions, mutation, deformed, extra digits, fewer digits, missing arms, missing legs, signature, watermark, username
- CFG: 4-5
- Sampling steps: 30-50
- Sampler: Euler a or ER SDE
- Scheduled type: Normal
- Standard Resolution:
832 x 1216, 1216 x 832, 1152 x 896, 896 x 1152, 1344 x 768, 768 x 1344, 1024 x 1024
Acknowledgements
A special thanks to the community and the developers who made this project possible:
- Circlestone Labs: For providing the incredible open-source Anima base model.
- Kohya_ss & Contributors: For the comprehensive and powerful open-source training framework
Support
If you’d like to support this project or my other developments, you can buy me a coffee on Ko-Fi
License
- Downloads last month
- 33