Anima Control Pose Preview-2: Native Pose Control for ComfyUI

A new pose control adapter for the Anima v1.0 image model has been released — Anima Control Pose Preview-2 brings skeleton-based pose conditioning to Anima with native ComfyUI custom nodes, multi-resolution support, and substantially improved pose-following accuracy.

What It Does

Anima Control Pose is a channel-concat control-LoRA that conditions Anima image generation on a skeleton pose map. Given a reference photo, the ComfyUI node detects the pose and renders a skeleton, which the model follows during generation — enabling precise control over character positioning, gestures, and body language in AI-generated images.

Preview-2 is a major update over Preview-1 with:

• Multi-resolution support: 512, 768, and 1024 px (Preview-1 was 512-only)
• Larger training corpus — cleaner anatomy and steadier poses
• New ComfyUI node "Anima Pose Control" — auto-detects pose from a reference photo with multiple skeleton rendering styles (thin, thick, puppet, heatmap, with/without hands and face)
• Body-PCK@0.1: ~0.83 at 1024 resolution (vs ~0.59 for Preview-1 at 512)

Method

The control adapter uses a zero-initialized ControlEmbedder that produces control tokens added to the frozen base patch-embed output, plus a rank-16 low-rank adapter on the transformer blocks. The base Anima model, text encoder, and VAE remain frozen.

At strength = 0, the adapter is exactly the base model — the control contribution grows only as it earns loss during training.

Setting	Value
Resolution	512 + 768 + 1024, aspect-ratio bucketed
Adapter rank	16
Control dropout	0.1
Precision	bf16

Usage in ComfyUI

The release ships with everything needed for a seamless ComfyUI experience:

1. Installation: Place anima_pose_preview2.safetensors in ComfyUI/models/loras/, then copy the two custom node folders (anima_control_lora/ and ComfyUI-anima-pose-control/) into ComfyUI/custom_nodes/
2. Workflows: Four included .json workflows — demo (control vs no-control side-by-side), simple, edit, and compare (one pose across all skeleton styles)
3. Pose detection: The Anima Pose Control node auto-downloads DWPose ONNX models (~316 MB) on first use; works offline after caching

Availability

Anima Control Pose Preview-2 is available on Hugging Face under a non-commercial license:

• HF Repo: czxkck/Anima-Control-Pose
• Main file: anima_pose_preview2.safetensors (place in ComfyUI/models/loras/)
• Custom nodes: Included in the repo under comfyui/
• Base model: Anima v1.0 by Circlestone Labs (required)

The author notes that Preview-2 is still experimental — while significantly improved, it can still miss poses or produce artifacts on complex poses. A Preview-3 is in development with a focus on better skeleton representation and a purpose-built anime pose detector.