Raehoshi Anima

Raehoshi AnimaRaehoshi 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 & RequirementsImportant 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 Guideraehoshi-anima-v1.0.safetensors goes in ComfyUI/models/diffusion_modelsqwen_3_06b_base.safetensors goes in ComfyUI/models/text_encodersqwen_image_vae.safetensors goes in ComfyUI/models/vaeRecommended SettingsFor the optimal experience and the highest quality generations, we recommend the following configurations:Sampler: Euler a or ER SDESchedule Type: Beta or NormalSteps: 32CFG Scale: 4.0 – 5.0Resolution: Any resolution up to 1536 (ensure dimensions are divisible by 32)Positive Prompt: masterpiece, best quality, score_7, absurdresNegative Prompt: worst quality, low quality, score_1, score_2, score_3, artist name, blurry, jpeg artifacts, bad anatomy, bad hands, bad proportions, mutation, deformed, extra digits, fewer digits, missing arms, missing legsPrompting TipsTag 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 DetailsRaehoshi 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 ExpansionDataset Size: ~25k imagesTrained Resolution: 1024x1024Hardware: NVIDIA RTX PRO 6000 (96GB VRAM)Batch Size: 32Gradient accumulation steps: 1Learning Rate: 1.5e-6 (LLM Adapter LR: 2e-7)Focus: Introducing new franchises, series, and character knowledge.Stage 2: Aesthetic & Style RefinementDataset Size: ~1k high-curation imagesTrained Resolution: Multi-aspect (1024x1024 & 1536x1536)Hardware: NVIDIA RTX PRO 6000 (96GB VRAM)Batch Size: Per-resolution batch size (24-1536x1536) & (48-1024x1024)Gradient accumulation steps: 1Learning Rate: 1e-6 (LLM Adapter LR: 0)Focus: Mitigating artifacts, balancing composition, and enhancing the overall visual style.List of New Series/Characters Trained:Expanded Knowledge Base (Up to May 2026)The model’s character and lore library has been updated to include the latest data for:Zenless Zone ZeroWuthering WavesHonkai: Star RailGenshin ImpactArknights: EndfieldNeverness to EvernessFor character trait details prompts, please refer to the Danbooru site for accurate tags and references.Special ThanksA huge thank you to GSlinux for providing the development support needed to make this project a reality.Support the DevelopmentIf 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-fiLicenseThis model is released under the CircleStone Labs Non-Commercial License.