Anima Role Ref KV · v2.0

Generate new poses, outfits, expressions, and scenes from a single character reference image and a text prompt on **Anima Base v1.0**, without per-character training or trigger words.

Required downloads: anima-role-ref-kv-v2.0.safetensors AND anima-role-ref-kv-comfyui-setup-v2.0.zip (Training Data / Attachments).

v2.0 ships **BF16 weights** (50% smaller). If upgrading from v1.0, you MUST replace ComfyUI/custom_nodes/anima-role-ref-kv from the new setup ZIP and restart ComfyUI — older FP32-only nodes will reject BF16 files. The updated node supports both v2.0 and v1.0. v2.0 is 15% faster by using BF16 for all calculations.

[Hugging Face Repository (Diffusers + ComfyUI)] · [Online Demo Space]

What changed in v2.0

- **Higher character resemblance**: normalized head similarity 1.23 -> 1.72 across 3,008 development evaluations.

- **Far fewer washed-out outputs on natural-language prompts**: unintended low-color rate drops from 31.1% to 3.2%.

- **Tradeoff**: overall tag hit rate is 90.3% (vs 91.2% in v1.0); stronger preservation of reference rendering and garment details can sometimes resist heavy outfit or style changes.

Quick Start (ComfyUI)

1. Extract anima-role-ref-kv-comfyui-setup-v2.0.zip and copy custom_nodes/anima-role-ref-kv into ComfyUI/custom_nodes/.

2. Put anima-role-ref-kv-v2.0.safetensors into ComfyUI/models/loras/.

3. Restart ComfyUI and load workflows/anima-role-ref-kv-v2.0.json (requires anima-base-v1.0.safetensors, qwen_3_06b_base.safetensors, qwen_image_vae.safetensors).

### Recommended Settings & Prompting

- **Sampling**: **28 steps, CFG 4, BF16**, ~1 MP 832 x 1216, 1024 x 1024, or 1216 x 832, multiples of 16).

- **Tag prompt**: highres, safe, 1girl, solo, upper body, sitting, bench, park, tree (do not repeat the reference character's existing hair/eye traits).

- **Natural-language prompt**: safe, 1girl. Upper body shot from the waist up. She is sitting on a bench in a park with trees.

- **Negative prompt**: worst quality, low quality, score_1, score_2, score_3, artist name, blurry, jpeg artifacts, chromatic aberration

Independent modified derivative of Anima, subject to the [CircleStone Non-Commercial License](https://huggingface.co/circlestone-labs/Anima-Base-v1.0-Diffusers/blob/main/LICENSE.md); not an official CircleStone Labs product.