mirror of
https://github.com/snapotter-hq/SnapOtter.git
synced 2026-08-03 07:46:42 +02:00
stirling-imageandGitHub
b0083e2b08
Merge CPU, CUDA, and lite Docker images into a single unified image. One tag (latest) works on all platforms: amd64 (NVIDIA CUDA) and arm64 (CPU). GPU auto-detected at runtime. All ML models and packages baked in. Key changes: - Platform-conditional Dockerfile (nvidia/cuda on amd64, node on arm64) - tini as PID 1 for proper signal handling - Fix FILES_STORAGE_PATH data loss bug - Fix RealESRGAN upscaler (was broken, always fell back to Lanczos) - Fix PaddleOCR language codes and stdout corruption - Simplified CI/CD (single build, single tag) - Expanded model pre-download with verification - Shutdown timeout, improved health endpoint - Remove unused lama-cleaner
11 lines
199 B
Plaintext
11 lines
199 B
Plaintext
rembg==2.0.62
|
|
realesrgan==0.3.0
|
|
paddleocr==2.9.1
|
|
paddlepaddle-gpu==3.0.0
|
|
mediapipe==0.10.21
|
|
onnxruntime-gpu==1.20.1
|
|
numpy==1.26.4
|
|
Pillow==11.1.0
|
|
opencv-python-headless==4.10.0.84
|
|
seam-carving==1.1.0
|