feat: initial implementation of Real-ESRGAN Web UI
Full-featured Gradio 6.0+ web interface for Real-ESRGAN image/video upscaling, optimized for RTX 4090 (24GB VRAM). Features: - Image upscaling with before/after comparison (ImageSlider) - Video upscaling with progress tracking and checkpoint/resume - Face enhancement via GFPGAN integration - Multiple codecs: H.264, H.265, AV1 (with NVENC support) - Batch processing queue with SQLite persistence - Processing history gallery - Custom dark theme - Auto-download of model weights 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
30
requirements.txt
Normal file
30
requirements.txt
Normal file
@@ -0,0 +1,30 @@
|
||||
# Real-ESRGAN Web UI Dependencies
|
||||
|
||||
# Gradio UI Framework
|
||||
gradio>=6.0.0
|
||||
gradio-imageslider>=0.0.20
|
||||
|
||||
# PyTorch (CUDA 12.1)
|
||||
--extra-index-url https://download.pytorch.org/whl/cu121
|
||||
torch>=2.0.0
|
||||
torchvision>=0.15.0
|
||||
|
||||
# Real-ESRGAN and dependencies
|
||||
realesrgan>=0.3.0
|
||||
basicsr>=1.4.2
|
||||
|
||||
# Face Enhancement
|
||||
gfpgan>=1.3.8
|
||||
facexlib>=0.3.0
|
||||
|
||||
# Video Processing
|
||||
av>=10.0.0
|
||||
|
||||
# Image Processing
|
||||
opencv-python>=4.8.0
|
||||
Pillow>=10.0.0
|
||||
numpy>=1.24.0
|
||||
|
||||
# Utilities
|
||||
tqdm>=4.65.0
|
||||
requests>=2.28.0
|
||||
Reference in New Issue
Block a user