Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Create Dockerfile

Update README.md

chore: remove autotune_cache.json from tracking and add to .gitignore

feat: support manual FOV input (deg/rad) with auto MoGe-2 fallback

Rename Local Deploy to Free Deploy Server; fix progress tracking with global var

Add Recommended and Free tags to Local Deploy button

Update README.md

Update app_file to app_proxy.py in README

Add Local Deploy button linking to HuggingFace Pixal3D-Server

update: README description and Space metadata

fix: use js_on_load for queue polling, direct CORS fetch to gradio share links

update app.py

feat: multi-instance cards with 2x2 grid layout, larger UI, white button text

feat: add visible queue counter badge in sidebar

fix: prevent page height growing infinitely and open redirect in new tab

chore: update app.py, add app_bak.py, update requirements and autotune cache

feat: add local deployment with queue system and HF proxy

Revert to torch2.6+cu124 for HF Space compatibility, backup th28 requirements

Fix: total_mem -> total_memory

Fix: move GPU diagnostics into init_models() to avoid early CUDA init before spaces import

Add GPU/CUDA diagnostics at startup

Update to torch2.8+cu128 environment and rename Render Mode

Fix progress tracking: replace SSE+queue with file-based polling for HF Spaces compatibility

fix: progress not showing on 2nd extract - recreate queue and re-fetch ref in SSE loop

fix: destroy and recreate model-viewer to prevent stale mesh display

Remove unused example images