Upgrade rembg to use BiRefNet model (state-of-the-art)

- Use onnxruntime>=1.17.0 (fixed executable stack issues, no execstack needed)
- Use rembg>=2.0.70 with BiRefNet model support
- Update all remove-background endpoints to use birefnet-general model
- BiRefNet provides better edge detection and matting quality than u2net
- Falls back to default model if BiRefNet unavailable
This commit is contained in:
Claude
2026-01-27 14:34:28 +00:00
parent 44bc5ed2f5
commit 2ab9ed7559
3 changed files with 34 additions and 18 deletions
+4 -3
View File
@@ -14,9 +14,10 @@ pydantic-settings==2.1.0
email-validator==2.1.0
opencv-python-headless==4.9.0.80
scikit-image==0.22.0
# rembg for background removal - use onnxruntime 1.14.1 to avoid executable stack issue in Docker
onnxruntime==1.14.1
rembg==2.0.50
# rembg for background removal with BiRefNet models (state-of-the-art)
# Using latest onnxruntime (1.17+ fixed executable stack issues)
onnxruntime>=1.17.0
rembg>=2.0.70
# SAM (Segment Anything) for smart object selection - runs locally, no API needed
torch==2.1.2
torchvision==0.16.2