Update readme
This commit is contained in:
41
readme
41
readme
@@ -1,29 +1,30 @@
|
|||||||
# 🔪 ComfyUI Sharp Frame Selector
|
# 🔪 ComfyUI Sharp Frame Selector
|
||||||
|
|
||||||
A suite of custom nodes for [ComfyUI](https://github.com/comfyanonymous/ComfyUI) designed to intelligently extract the sharpest frames from video footage.
|
A collection of high-performance custom nodes for **ComfyUI** designed to detect blur, calculate sharpness scores, and automatically extract the best frames from videos or image batches.
|
||||||
|
|
||||||
Based on the [sharp-frames](https://github.com/Reflct/sharp-frames-python) logic, this tool uses **Laplacian Variance** to score image clarity. It is optimized for high-resolution video processing using a **Sidechain Workflow** that saves massive amounts of RAM.
|
This pack includes two distinct approaches:
|
||||||
|
1. **Parallel Video Loader:** A multi-threaded, path-based loader for processing massive video files directly from disk (Low RAM usage).
|
||||||
## ✨ Key Features
|
2. **Standard Sharpness Duo:** A classic filter setup for processing images/latents *inside* your existing workflow.
|
||||||
|
|
||||||
* **Sidechain Optimization:** Analyze lightweight 512px proxy images to control the selection of heavy 4K raw frames.
|
|
||||||
* **Batched Extraction:** Splits video into time slots (e.g., 1 second) and picks the single best frame from each slot. Perfect for ensuring action scenes are not missed.
|
|
||||||
* **Threshold Filtering:** Automatically discards frames that are too blurry, even if they are the "winner" of their batch.
|
|
||||||
* **Buffer Control:** Optional dead-zones between batches to reduce frame count or ensure temporal separation.
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## 🚀 Installation
|
## 🚀 Key Features
|
||||||
|
|
||||||
### Option 1: ComfyUI Manager (Recommended)
|
### 1. New: Parallel Video Loader (Path-Based)
|
||||||
1. Open ComfyUI Manager.
|
* **Zero-RAM Scanning:** Scans video files directly from disk without decoding every frame to memory.
|
||||||
2. Search for **"Sharp Frame Selector"**.
|
* **Multi-Threaded:** Uses all CPU cores to calculate sharpness scores at high speed.
|
||||||
3. Click **Install**.
|
* **Batching Support:** Includes a "Page" system to process long movies in chunks (e.g., minute-by-minute) without restarting ComfyUI.
|
||||||
|
* **Smart Selection:** Automatically skips "adjacent" frames to ensure you get a diverse selection of sharp images.
|
||||||
|
|
||||||
### Option 2: Manual Installation
|
### 2. Standard Sharpness Duo (Tensor-Based)
|
||||||
Clone this repository into your `custom_nodes` folder:
|
* **Workflow Integration:** Works with any node that outputs an `IMAGE` batch (e.g., AnimateDiff, VideoHelperSuite).
|
||||||
|
* **Precision Filtering:** Sorts and filters generated frames before saving or passing to a second pass (img2img).
|
||||||
|
|
||||||
```bash
|
---
|
||||||
cd ComfyUI/custom_nodes/
|
|
||||||
git clone [https://github.com/YOUR_USERNAME/ComfyUI-Sharp-Selector.git](https://github.com/YOUR_USERNAME/ComfyUI-Sharp-Selector.git)
|
## 📦 Installation
|
||||||
pip install -r ComfyUI-Sharp-Selector/requirements.txt
|
|
||||||
|
1. Clone this repository into your `custom_nodes` folder:
|
||||||
|
```bash
|
||||||
|
cd ComfyUI/custom_nodes/
|
||||||
|
git clone [https://github.com/ethanfel/ComfyUI-Sharp-Selector.git](https://github.com/ethanfel/ComfyUI-Sharp-Selector.git)
|
||||||
Reference in New Issue
Block a user