fix: add CLIPVision input to IPAdapterAdvanced nodes

IPAdapterAdvanced requires a direct CLIPVision input, unlike the basic
IPAdapter node. Added CLIPVisionLoader nodes to both workflows:

Face workflow:
- Added CLIPVisionLoader (node 12) loading CLIP-ViT-bigG-14
- Connected to IPAdapterAdvanced (node 4) via link 20

Composition workflow:
- Added CLIPVisionLoader (node 15) loading CLIP-ViT-bigG-14
- Connected to both IPAdapterAdvanced nodes (6 and 7) via links 25 and 26

This provides the required CLIP Vision model for image understanding
in the IP-Adapter processing pipeline.

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

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

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

@@ -1,6 +1,6 @@
 {
-  "last_node_id": 18,
-  "last_link_id": 25,
+  "last_node_id": 19,
+  "last_link_id": 27,
   "nodes": [
     {
       "id": 1,
@@ -263,6 +263,11 @@
           "name": "image",
           "type": "IMAGE",
           "link": 5
+        },
+        {
+          "name": "clip_vision",
+          "type": "CLIP_VISION",
+          "link": 25
         }
       ],
       "outputs": [
@@ -317,6 +322,11 @@
           "name": "image",
           "type": "IMAGE",
           "link": 8
+        },
+        {
+          "name": "clip_vision",
+          "type": "CLIP_VISION",
+          "link": 26
         }
       ],
       "outputs": [
@@ -598,6 +608,39 @@
           "link": 21
         }
       ]
+    },
+    {
+      "id": 15,
+      "type": "CLIPVisionLoader",
+      "pos": [
+        450,
+        250
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "widgets_values": [
+        "CLIP-ViT-bigG-14-laion2B-39B-b160k.bin"
+      ],
+      "title": "CLIP Vision Loader",
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "properties": {
+        "Node name for S&R": "CLIPVisionLoader"
+      },
+      "outputs": [
+        {
+          "name": "CLIP_VISION",
+          "type": "CLIP_VISION",
+          "links": [
+            25,
+            26
+          ],
+          "slot_index": 0
+        }
+      ]
     }
   ],
   "links": [
@@ -744,6 +787,22 @@
       14,
       0,
       "IMAGE"
+    ],
+    [
+      25,
+      15,
+      0,
+      6,
+      3,
+      "CLIP_VISION"
+    ],
+    [
+      26,
+      15,
+      0,
+      7,
+      3,
+      "CLIP_VISION"
     ]
   ],
   "extra": {

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

@@ -1,6 +1,6 @@
 {
-  "last_node_id": 15,
-  "last_link_id": 20,
+  "last_node_id": 16,
+  "last_link_id": 21,
   "nodes": [
     {
       "id": 1,
@@ -178,6 +178,11 @@
           "name": "image",
           "type": "IMAGE",
           "link": 3
+        },
+        {
+          "name": "clip_vision",
+          "type": "CLIP_VISION",
+          "link": 20
         }
       ],
       "outputs": [
@@ -459,6 +464,38 @@
           "link": 15
         }
       ]
+    },
+    {
+      "id": 12,
+      "type": "CLIPVisionLoader",
+      "pos": [
+        450,
+        250
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "widgets_values": [
+        "CLIP-ViT-bigG-14-laion2B-39B-b160k.bin"
+      ],
+      "title": "CLIP Vision Loader",
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "properties": {
+        "Node name for S&R": "CLIPVisionLoader"
+      },
+      "outputs": [
+        {
+          "name": "CLIP_VISION",
+          "type": "CLIP_VISION",
+          "links": [
+            20
+          ],
+          "slot_index": 0
+        }
+      ]
     }
   ],
   "links": [
@@ -573,6 +610,14 @@
       11,
       0,
       "IMAGE"
+    ],
+    [
+      20,
+      12,
+      0,
+      4,
+      3,
+      "CLIP_VISION"
     ]
   ],
   "extra": {