Install httpx and capture disconnect snapshots

feat(gpu): switch to onnxruntime-gpu for CUDAExecutionProvider

fix(codeformer): clone repo inside models path and add facexlib dependency

feat(pipeline): lazy insightface import + add onnxruntime/onnx/torch deps

Pivot: remove GFPGAN + reenactment stack; CodeFormer-only enhancement, purge legacy files, update docs & downloader

GPU-only: enforce CUDA EP when required; switch container to CUDA 11.8 + Torch cu118 to match ORT; add MIRAGE_REQUIRE_GPU=1

Upgrade to CUDA 12.1 + Torch cu121; bump ORT GPU to 1.18.1; use myn0908 generator_fix_grid (opset20); drop TensorRT plugin

ORT ext + robust generator loading: add onnxruntime-extensions, register custom ops; validate ONNX downloads and retry with alt URLs; keep shape inference disabled

Fix build: pin onnxruntime-gpu to 1.16.3 (available on PyPI, CUDA 11.x friendly)

Align Space image to CUDA 11.8 (Torch cu118, ORT GPU 1.17.3); add rotated-image fallback for set_reference

Fix MediaPipe dependency and enhance WebRTC debugging

Clean up requirements.txt - remove duplicates and conflicts

Fix Space runtime error - remove MediaPipe dependency and build optimizations

Add landmark reenactor fallback and LivePortrait ONNX URLs

feat(docker): switch to Docker Space GPU runtime; prod WebRTC (aiortc) flow; remove legacy WS; token auth; instrumentation p50/p95; requirements harden

Fix duplicate numpy pin (remove 1.24.0, keep 1.26.4)

Optimize for HuggingFace Spaces: simplified Gradio interface and reduced dependencies

feat(docker-gpu): switch to CUDA-enabled PyTorch base and add torch deps

feat: phase1-2 baseline echo scaffold