fix: clean up duplicate closing tags at end of showcase container in index.html

Redesign index.html into premium SAM 3 style landing page layout with floating search

Switch to size='xlarge' GPU pool to route past faulty hardware ECC nodes

Fix UI crash in index.html by guarding outputEmpty element references

Fix ZeroGPU model loading in app.py via lazy-loading initialization

Fix prediction payload serialization style for Gradio Server API

Fix example loading, file upload and ZeroGPU compatibility

redesign

minimal redesign

redesign

Fix programmatic file load activeFile reset bug in index.html

Update default model to nvidia/LocateAnything-3B and transformers version

Update Gradio SDK version to 6.14.0 in README.md

Convert to gradio.Server with premium custom HTML/CSS/JS frontend

fix(log): write one JSONL file per record with session_id to prevent overwrite

docs: switch arXiv citation to tags+body link format

docs: cite arXiv 2605.27365 in README to link Space from paper page

ui: add resolution note next to header about magi-attention / 1K resize

fix(requirements): bump torch to 2.8.0 / torchvision to 0.23.0 for ZeroGPU compatibility

Update README.md

fix private auth and zerogpu build

demo

initial commit