comfyui: bake qwen_image21 patch into image via startup wrapper

The qwen_image21 detection check and GGUF node arch list patch are
applied by a startup wrapper (comfyui-start.sh) that runs before
ComfyUI starts. The patch script and wrapper are baked into the image
so they survive container recreations. The quadlet's Exec now points
at the wrapper instead of main.py directly.

dankclaw/Containerfile.comfyui

@@ -21,4 +21,19 @@ RUN mkdir -p /opt/ComfyUI/models /opt/ComfyUI/input /opt/ComfyUI/output /opt/Com
 RUN grep -viE '^(torch|torchvision|torchaudio)([^a-z]|$)' requirements.txt > /tmp/req-notorch.txt \
     && pip install --no-cache-dir -r /tmp/req-notorch.txt
 
+# The city96/ComfyUI-GGUF custom node (loaded from the host's custom_nodes
+# volume) needs the gguf library to decode GGUF-quantized diffusion models.
+# sentencepiece and protobuf are its optional tokenizer deps. Baking them into
+# the image keeps the dependency across container recreations — the node itself
+# lives in the host volume, which persists, but the Python env does not.
+RUN pip install --no-cache-dir "gguf>=0.13.0" sentencepiece protobuf
+
+# Bake the qwen_image21 patch script into the image. It is run by the
+# startup wrapper before ComfyUI starts, so the patch survives container
+# recreations (the model_detection.py file is in the image, not a volume).
+COPY apply_qwen21_patch.py /opt/ComfyUI/apply_qwen21_patch.py
+COPY comfyui-start.sh /opt/ComfyUI/comfyui-start.sh
+RUN chmod +x /opt/ComfyUI/comfyui-start.sh
+
+CMD ["/opt/ComfyUI/comfyui-start.sh"]
 EXPOSE 8188