ComfyUI-Impact-Pack (FaceDetailer)
Automatically detects faces, hands, or objects with YOLO/SAM, crops them to high resolution, inpaints details, and blends them back seamlessly. Package: ltdrdata/ComfyUI-Impact-Pack.
Updated Oct 17, 2026 · 1 min read
- Node / Pack
- ComfyUI-Impact-Pack (FaceDetailer)
- Category
- custom-pack
- Inputs
- image, model, clip, vae, positive, negative, bbox_detector, sam_model_opt
- Outputs
- IMAGE, cropped_refined, mask
- Source Pack
- ltdrdata/ComfyUI-Impact-Pack
What ComfyUI-Impact-Pack (FaceDetailer) does in a ComfyUI graph
Automatically detects faces, hands, or objects with YOLO/SAM, crops them to high resolution, inpaints details, and blends them back seamlessly.
On the canvas, this node accepts `image, model, clip, vae, positive, negative, bbox_detector, sam_model_opt` and emits `IMAGE, cropped_refined, mask`. Every pin is color-coded by data type so you cannot accidentally wire a pixel `IMAGE` tensor into a `LATENT` pin without an intermediate encode step.
Installation and missing-node recovery on Windows
ComfyUI-Impact-Pack (FaceDetailer) is provided by `ltdrdata/ComfyUI-Impact-Pack`. Open ComfyUI-Manager, click **Install Custom Nodes** (or **Install Missing Custom Nodes** if you loaded a workflow with red boxes), and restart the server.
Download the full Windows desktop or portable package at /download to get started with a clean Python 3.12 environment.
FAQs
How do I fix "ComfyUI-Impact-Pack (FaceDetailer)" showing up as a red box in ComfyUI?
Open ComfyUI-Manager, click **Install Missing Custom Nodes**, install `ltdrdata/ComfyUI-Impact-Pack`, and restart ComfyUI.
What are the main inputs and outputs of ComfyUI-Impact-Pack (FaceDetailer)?
Inputs: image, model, clip, vae, positive, negative, bbox_detector, sam_model_opt. Outputs: IMAGE, cropped_refined, mask.
Run on your hardware. Free forever.
The full ComfyUI engine: open source, fast, extensible, and yours to run however you want. Download the desktop app and open this workflow on your own machine.
