Add prefetch-models.sh to download AI models on host when container DNS is blocked

Lets SAM, U2Net, BEN2, and BiRefNet-HR (optionally SDXL via --sdxl) be
downloaded outside Docker into ./data/, which is already bind-mounted
into the GPU container — so a blocked container network no longer blocks
first-run setup. Reuses the existing dual-mode download_sam_model.py and
download_u2net_model.py as-is. For the HuggingFace Hub models, sets
HF_HOME (rather than --cache-dir) so the host-side cache layout matches
the container's default ~/.cache/huggingface resolution exactly, avoiding
a path-nesting mismatch between the two.

Wired into install-local-gpu.sh's completion banner and
bring-up-local-gpu.sh's header, and referenced from the relevant README
troubleshooting sections and the hf_cache bind-mount comment in
docker-compose.gpu.yml.

install-local-gpu.sh

@@ -162,4 +162,8 @@ echo ""
 echo "=================================================="
 echo "  Setup complete."
 echo "  Start the app with:  ./bring-up-local-gpu.sh"
+echo ""
+echo "  If models fail to download inside the container (DNS/firewall"
+echo "  blocked), fetch them on the host first instead:"
+echo "    ./prefetch-models.sh"
 echo "=================================================="