fix: use CLIP-ViT-bigG for IP-Adapter face workflow

Change CLIP vision model from ViT-H to ViT-bigG to match the
VIT-G preset in IPAdapterUnifiedLoader. This fixes dimension
mismatch error (1280 vs 768).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

comfyui/workflows/image-to-image/ipadapter-face-i2i-production-v1.json

@@ -477,7 +477,7 @@
         "1": 58
       },
       "widgets_values": [
-        "CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors"
+        "CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors"
       ],
       "title": "CLIP Vision Loader",
       "flags": {},