Fix quality loss by avoiding patch downscaling and improving text-erase crop

Add /remove_bg endpoint using rembg (u2net ONNX) for CPU background removal

Fix dependency version conflicts for Hugging Face deployment

Add /text_erase: single-call text-prompt object removal (CLIPSeg+LaMa)

Add CLIPSeg text-based segmentation endpoint /segment_text

Fix: remove duplicate torch import causing UnboundLocalError in _load_realesrgan

Align with healthy gemini-eraser-ai space: remove CLIPSeg/transformers, use RealESRGAN_x4plus.pth from GitHub

Fix: download RealESRGAN x4 from GitHub instead of COPY missing 4x-UltraSharp.pth

Fix model loading: use absolute paths, retry logic, proper model assignment

Update backend with text segmentation, UltraSharp, and lossless compositing

fix: resolve runtime error in main.py by correcting variable initialization

Optimize Real-ESRGAN CPU inference for Free Tier (1 thread, tile=128)

Fix basicsr torchvision compatibility by safely down-pinning TorchVision

Upgrade backend to use Real-ESRGAN

Update backend with Vanishly rebrand and AI upscaling capabilities

feat: FSRCNN AI upscaling endpoint via OpenCV dnn_superres (PRO feature)

perf: async LaMa offload, JPEG response, server-side downscale, faster FastSAM

Optimize FastSAM inference for extremely low latency

Bake FastSAM weights into Docker image to avoid RO filesystem error

Fix HF glib dependencies

Fix form inputs for FastAPI

Add FastSAM cloud segment endpoint

chore: update project metadata, dependencies, and Docker configuration

Initial commit for HF Spaces backend