Official Release and Open Weight will be available at 2026/06/18

Raehoshi Anima

Raehoshi Anima is an enhanced iteration built upon the Anima Base v1.0 architecture. This release focuses on elevating visual style, integrating extensive new concepts, and expanding character knowledge. The ultimate goal is to deliver a more polished, balanced, and visually stunning output while remaining faithful to the core strengths of the base model.

🚀 Installation & Requirements

⚠️ Important Note: This model does not include a built-in Text Encoder or VAE. You must download these components separately to achieve the intended results.

File Placement Guide

⚙️ Recommended Settings

For the optimal experience and the highest quality generations, we recommend the following configurations:

• Sampler: Euler a or Euler SDE
• Schedule Type: Beta or Normal
• Steps: 32
• CFG Scale: 4.0 – 5.0
• Resolution: Any resolution up to 1536 (ensure dimensions are divisible by 32)
• Positive Prompt: masterpiece, best quality, score_7, absurdres
• Negative Prompt: worst quality, low quality, score_1, score_2, score_3, artist name, blurry, jpeg artifacts, bad , bad hands, bad proportions, mutation, deformed, extra digits, fewer digits, missing arms, missing legs

💡 Prompting Tips

• Tag Ordering: For the most consistent results, follow this structured prompt order:[Quality / Meta / Year / Safety tags] ➔ [1girl / 1boy / Character Count] ➔ [Character Name] ➔ [Series / Copyright] ➔ [Artist] ➔ [General Tags]
• Character Accuracy: Always include the official series/copyright tags alongside the character name to significantly improve details and accuracy.
• Hybrid Prompting: The model handles hybrid prompting seamlessly. Feel free to mix dan match danbooru-style tags with natural language descriptions (e.g., use tags for characters and natural language for background/action).

🔬 Training Details

Raehoshi Anima was trained using a custom personal fork of Diffusion-pipe across a comprehensive two-stage fine-tuning process. The dataset utilizes multi-level captioning with random selection and tag dropout to ensure flexibility.

Stage 1: Concept & Character Expansion

• Dataset Size: ~25,000 images
• Trained Resolution: 1024x1024
• Hardware: NVIDIA RTX 6000 Ada (96GB VRAM)
• Batch Size: 32
• Learning Rate: 1.5e-6 (LLM Adapter LR: 2e-7)
• Focus: Introducing new franchises, series, and character knowledge.

Stage 2: Aesthetic & Style Refinement

• Dataset Size: ~1,000 high-curation images
• Trained Resolution: Multi-aspect (1024x1024 & 1536x1536)
• Hardware: NVIDIA RTX 6000 Ada (96GB VRAM)
• Batch Size: 24
• Learning Rate: 1e-6 (LLM Adapter LR: 0)
• Focus: Mitigating artifacts, balancing composition, and enhancing the overall visual style.

Special Thanks

A huge thank you to GSlinux for providing the crucial infrastructure and development support needed to make this project a reality.

Support the Development

If you love using this model and want to help fund future iterations and dataset curation, consider supporting the project:

• ⚡ Send a tip of Yellow Buzz directly on this platform.
• ☕ Buy me a coffee via Ko-fi (Insert link here)

📄 License

This model is released under the CircleStone Labs Non-Commercial License.