Anime Eye Detector (YOLOv8)

Also available on Hugging Face🤗: https://huggingface.co/killjoyelite/anime-eye-yolov8

A YOLOv8 object detection model fine-tuned to detect eyes in anime-style character art, intended for use with ComfyUI + Impact Pack for automated eye detailing/inpainting workflows (similar to how face_yolov8n.pt and hand_yolov8n.pt are used).

Model details

• Base model: YOLOv8n / YOLOv8s (Ultralytics)

• Task: Object detection, single class (eye)

• Training data: 286 self-generated anime and semi-realistic style images (AI-generated, primarily female characters), manually labeled with bounding boxes around each visible eye

• Training config: 100 epochs, image size 640, batch size 8

Performance (on validation split)

Known limitations

• Detection on male character eyes is improved as of v2.0 but still less reliable than on female characters.

• Trained on anime and semi-realistic style images — also tested well on realistic styles, though not extensively validated across every art style.

• Dataset size (286 images as of v2.0) — strong validation metrics, but a larger dataset would improve robustness further.

If you find specific failure cases, feel free to open a discussion — this is a good candidate for community-driven dataset expansion over time.

Examples

Detection preview — the model correctly finds eyes across different poses/styles:

Eye color change/Eye fixing — using the detected eye region with Detailer (SEGS) to redraw eye color/detail from a prompt, while keeping the rest of the image untouched:

Usage (ComfyUI)

Easiest method: Search "eye" in ComfyUI-Manager's Install Models menu and install directly — no manual download needed.

Manual method:

1. Download the model file — Civitai renames files automatically (e.g. animeEyeDetector_v20.pt)

2. (Optional) Rename it to something clear, like eye_yolov8n.pt or eye_yolov8s.pt depending on which size you downloaded — this just determines what shows up in the dropdown menu, doesn't affect how it works.

3. Place it in:

   ComfyUI/models/ultralytics/bbox/
   

4. Restart ComfyUI.

5. In your workflow:

   Load Image → UltralyticsDetectorProvider (select the eye detector model) → BboxDetectorSEGS → Detailer (SEGS)
   

6. Recommended Detailer (SEGS) starting settings for eye detailing:

   • guide_size: 512

   • denoise: 0.5–0.7 (lower = closer to the original eye, higher = more prompt-driven reinterpretation)

   • feather: 5–10

License

Released under the MIT License. Training images were self-generated by the author; users should independently verify licensing terms of any base checkpoint used to generate their own training/inference images if that matters for their use case.