root/PaintPlus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix SAM symlink crash and make prefetch-models.sh resilient per-step

Browse Source 
download_sam_model.py crashed with an uncaught PermissionError when
data/models/ is root-owned (common after a prior Docker run) and a
non-root host user tries to recreate the convenience sam_model.pth
symlink — observed in the wild, and it aborted the whole prefetch run
before U2Net/BEN2/BiRefNet-HR were ever attempted. Worse, the same
unguarded symlink call sat inside the post-download try/except, so a
successful download could get deleted just because the symlink step
failed afterward. Wrapped symlink creation in a shared helper that
warns and continues instead of raising — the real model file already
satisfies entrypoint.sh's checks regardless of the symlink.

prefetch-models.sh now treats SAM, U2Net, and the HuggingFace models as
independent steps (one failing no longer aborts the rest) and prints a
summary of which steps failed, so a single run gives full diagnostic
signal instead of stopping at the first error.
This commit is contained in:
Claude
2026-06-18 16:33:17 +00:00
parent 3a977c7438
commit 851e255641
2 changed files with 50 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
prefetch-models.sh
+34 -18
View File
@@ -12,9 +12,11 @@
# ./prefetch-models.sh --sdxl # also prefetch SDXL base + inpaint (~13GB)
#
# Safe to re-run: every download here skips files that already exist
# (HuggingFace Hub) or are already present (SAM/U2Net).
# (HuggingFace Hub) or are already present (SAM/U2Net). Each model is
# independent — one failing (e.g. no network reachable at all) doesn't
# block the others from being attempted.
set -euo pipefail
set -uo pipefail
cd "$(dirname "$0")"
@@ -36,36 +38,39 @@ if [ "${1:-}" = "--sdxl" ]; then
PREFETCH_SDXL=1
fi
FAILED=()
echo "=================================================="
echo " Prefetching AI models (host-side, no Docker)"
echo "=================================================="
echo ""
echo "── SAM (Smart Select) ───────────────────────────────"
python3 scripts/download_sam_model.py vit_b
python3 scripts/download_sam_model.py vit_b || FAILED+=("SAM")
echo ""
echo "── U2Net (Remove Background fallback) ──────────────"
python3 scripts/download_u2net_model.py u2net
python3 scripts/download_u2net_model.py u2net || FAILED+=("U2Net")
echo ""
echo "── HuggingFace Hub models (BEN2, BiRefNet-HR) ───────"
if ! python3 -c "import huggingface_hub" &>/dev/null; then
echo "Installing huggingface_hub (lightweight — no torch/GPU needed for this step)..."
python3 -m pip install --quiet --user "huggingface_hub>=0.23.0"
python3 -m pip install --quiet --user "huggingface_hub>=0.23.0" || FAILED+=("huggingface_hub install")
fi
# HF_HOME must match what the container resolves by default: the bind mount
# maps ./data/hf_cache -> /root/.cache/huggingface, and the container never
# sets HF_HOME explicitly, so it defaults to ~/.cache/huggingface there.
# huggingface_hub itself appends "/hub" to HF_HOME to get the actual cache
# root (HF_HUB_CACHE) — setting HF_HOME here (instead of passing --cache-dir
# or cache_dir=... directly) lets both sides derive that "/hub" nesting the
# same way, rather than us hardcoding it and risking a mismatch.
export HF_HOME="$(pwd)/data/hf_cache"
if python3 -c "import huggingface_hub" &>/dev/null; then
# HF_HOME must match what the container resolves by default: the bind mount
# maps ./data/hf_cache -> /root/.cache/huggingface, and the container never
# sets HF_HOME explicitly, so it defaults to ~/.cache/huggingface there.
# huggingface_hub itself appends "/hub" to HF_HOME to get the actual cache
# root (HF_HUB_CACHE) — setting HF_HOME here (instead of passing --cache-dir
# or cache_dir=... directly) lets both sides derive that "/hub" nesting the
# same way, rather than us hardcoding it and risking a mismatch.
export HF_HOME="$(pwd)/data/hf_cache"
PREFETCH_SDXL="$PREFETCH_SDXL" python3 - << 'PYEOF'
PREFETCH_SDXL="$PREFETCH_SDXL" python3 - << 'PYEOF' || FAILED+=("HuggingFace models")
import os
from huggingface_hub import snapshot_download
@@ -81,12 +86,23 @@ for repo_id in repos:
snapshot_download(repo_id=repo_id, ignore_patterns=["*.msgpack", "flax_*", "tf_*"])
print(f" done: {repo_id}")
PYEOF
else
echo "⚠ Skipping BEN2/BiRefNet-HR — huggingface_hub unavailable (install failed above)"
FAILED+=("HuggingFace models")
fi
echo ""
echo "=================================================="
echo " Done. Models cached under ./data/models and ./data/hf_cache"
if [ "$PREFETCH_SDXL" != "1" ]; then
echo " (SDXL not included — re-run with --sdxl to also prefetch txt2img/inpaint, ~13GB)"
if [ ${#FAILED[@]} -eq 0 ]; then
echo " Done. Models cached under ./data/models and ./data/hf_cache"
if [ "$PREFETCH_SDXL" != "1" ]; then
echo " (SDXL not included — re-run with --sdxl to also prefetch txt2img/inpaint, ~13GB)"
fi
echo " Start the app: ./bring-up-local-gpu.sh"
else
echo " Finished with failures: ${FAILED[*]}"
echo " If ALL of the above failed, this host can't reach the internet right now"
echo " (check: curl -v https://github.com) — that's a host/network issue, not Docker."
echo " If only some failed, re-run this script to retry just those."
fi
echo " Start the app: ./bring-up-local-gpu.sh"
echo "=================================================="