Merge branch 'master' into fix/sqlalchemy-version-format

.github/workflows/tag-dispatch-cloud.yml

@@ -0,0 +1,45 @@
+name: Tag Dispatch to Cloud
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+jobs:
+  dispatch-cloud:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Send repository dispatch to cloud
+        env:
+          DISPATCH_TOKEN: ${{ secrets.CLOUD_REPO_DISPATCH_TOKEN }}
+          RELEASE_TAG: ${{ github.ref_name }}
+        run: |
+          set -euo pipefail
+
+          if [ -z "${DISPATCH_TOKEN:-}" ]; then
+            echo "::error::CLOUD_REPO_DISPATCH_TOKEN is required but not set."
+            exit 1
+          fi
+
+          RELEASE_URL="https://github.com/${{ github.repository }}/releases/tag/${RELEASE_TAG}"
+
+          PAYLOAD="$(jq -n \
+            --arg release_tag "$RELEASE_TAG" \
+            --arg release_url "$RELEASE_URL" \
+            '{
+              event_type: "comfyui_tag_pushed",
+              client_payload: {
+                release_tag: $release_tag,
+                release_url: $release_url
+              }
+            }')"
+
+          curl -fsSL \
+            -X POST \
+            -H "Accept: application/vnd.github+json" \
+            -H "Content-Type: application/json" \
+            -H "Authorization: Bearer ${DISPATCH_TOKEN}" \
+            https://api.github.com/repos/Comfy-Org/cloud/dispatches \
+            -d "$PAYLOAD"
+
+          echo "✅ Dispatched ComfyUI tag ${RELEASE_TAG} to Comfy-Org/cloud"

blueprints/Depth to Image (Z-Image-Turbo).json

@@ -160,7 +160,7 @@
         },
         "revision": 0,
         "config": {},
-        "name": "local-Depth to Image (Z-Image-Turbo)",
+        "name": "Depth to Image (Z-Image-Turbo)",
         "inputNode": {
           "id": -10,
           "bounding": [
@@ -2482,4 +2482,4 @@
     "VHS_KeepIntermediate": true
   },
   "version": 0.4
-}
+}

blueprints/Depth to Video (ltx 2.0).json

@@ -261,7 +261,7 @@
         },
         "revision": 0,
         "config": {},
-        "name": "local-Depth to Video (LTX 2.0)",
+        "name": "Depth to Video (LTX 2.0)",
         "inputNode": {
           "id": -10,
           "bounding": [
@@ -5208,4 +5208,4 @@
     "workflowRendererVersion": "LG"
   },
   "version": 0.4
-}
+}

blueprints/Image Edit (Flux.2 Klein 4B).json

@@ -128,7 +128,7 @@
         },
         "revision": 0,
         "config": {},
-        "name": "local-Image Edit (Flux.2 Klein 4B)",
+        "name": "Image Edit (Flux.2 Klein 4B)",
         "inputNode": {
           "id": -10,
           "bounding": [
@@ -1837,4 +1837,4 @@
     }
   },
   "version": 0.4
-}
+}

blueprints/Image Inpainting (Qwen-image).json

@@ -124,7 +124,7 @@
         },
         "revision": 0,
         "config": {},
-        "name": "local-Image Inpainting (Qwen-image)",
+        "name": "Image Inpainting (Qwen-image)",
         "inputNode": {
           "id": -10,
           "bounding": [
@@ -1923,4 +1923,4 @@
     "workflowRendererVersion": "LG"
   },
   "version": 0.4
-}
+}

blueprints/Image Outpainting (Qwen-Image).json

@@ -204,7 +204,7 @@
         },
         "revision": 0,
         "config": {},
-        "name": "local-Image Outpainting (Qwen-Image)",
+        "name": "Image Outpainting (Qwen-Image)",
         "inputNode": {
           "id": -10,
           "bounding": [
@@ -2749,4 +2749,4 @@
     }
   },
   "version": 0.4
-}
+}

blueprints/Image to Layers(Qwen-Image-Layered).json

@@ -1,15 +1,14 @@
 {
-  "id": "1a761372-7c82-4016-b9bf-fa285967e1e9",
   "revision": 0,
-  "last_node_id": 83,
+  "last_node_id": 176,
   "last_link_id": 0,
   "nodes": [
     {
-      "id": 83,
+      "id": 176,
-      "type": "f754a936-daaf-4b6e-9658-41fdc54d301d",
+      "type": "2d2e3c8e-53b3-4618-be52-6d1d99382f0e",
       "pos": [
-        61.999827823554256,
+        -1150,
-        153.3332507624185
+        200
       ],
       "size": [
         400,
@@ -56,6 +55,38 @@
             "name": "layers"
           },
           "link": null
+        },
+        {
+          "name": "seed",
+          "type": "INT",
+          "widget": {
+            "name": "seed"
+          },
+          "link": null
+        },
+        {
+          "name": "unet_name",
+          "type": "COMBO",
+          "widget": {
+            "name": "unet_name"
+          },
+          "link": null
+        },
+        {
+          "name": "clip_name",
+          "type": "COMBO",
+          "widget": {
+            "name": "clip_name"
+          },
+          "link": null
+        },
+        {
+          "name": "vae_name",
+          "type": "COMBO",
+          "widget": {
+            "name": "vae_name"
+          },
+          "link": null
         }
       ],
       "outputs": [
@@ -66,28 +97,41 @@
           "links": []
         }
       ],
+      "title": "Image to Layers (Qwen-Image-Layered)",
       "properties": {
         "proxyWidgets": [
           [
-            "-1",
+            "6",
             "text"
           ],
           [
-            "-1",
+            "3",
             "steps"
           ],
           [
-            "-1",
+            "3",
             "cfg"
           ],
           [
-            "-1",
+            "83",
             "layers"
           ],
           [
             "3",
             "seed"
           ],
+          [
+            "37",
+            "unet_name"
+          ],
+          [
+            "38",
+            "clip_name"
+          ],
+          [
+            "39",
+            "vae_name"
+          ],
           [
             "3",
             "control_after_generate"
@@ -95,6 +139,11 @@
         ],
         "cnr_id": "comfy-core",
         "ver": "0.5.1",
+        "ue_properties": {
+          "widget_ue_connectable": {},
+          "input_ue_unconnectable": {},
+          "version": "7.7"
+        },
         "enableTabs": false,
         "tabWidth": 65,
         "tabXOffset": 10,
@@ -103,25 +152,20 @@
         "secondTabOffset": 80,
         "secondTabWidth": 65
       },
-      "widgets_values": [
+      "widgets_values": []
-        "",
-        20,
-        2.5,
-        2
-      ]
     }
   ],
   "links": [],
-  "groups": [],
+  "version": 0.4,
   "definitions": {
     "subgraphs": [
       {
-        "id": "f754a936-daaf-4b6e-9658-41fdc54d301d",
+        "id": "2d2e3c8e-53b3-4618-be52-6d1d99382f0e",
         "version": 1,
         "state": {
-          "lastGroupId": 3,
+          "lastGroupId": 8,
-          "lastNodeId": 83,
+          "lastNodeId": 176,
-          "lastLinkId": 159,
+          "lastLinkId": 380,
           "lastRerouteId": 0
         },
         "revision": 0,
@@ -130,10 +174,10 @@
         "inputNode": {
           "id": -10,
           "bounding": [
-            -510,
+            -720,
-            523,
+            720,
             120,
-            140
+            220
           ]
         },
         "outputNode": {
@@ -156,8 +200,8 @@
             ],
             "localized_name": "image",
             "pos": [
-              -410,
+              -620,
-              543
+              740
             ]
           },
           {
@@ -168,8 +212,8 @@
               150
             ],
             "pos": [
-              -410,
+              -620,
-              563
+              760
             ]
           },
           {
@@ -180,8 +224,8 @@
               153
             ],
             "pos": [
-              -410,
+              -620,
-              583
+              780
             ]
           },
           {
@@ -192,8 +236,8 @@
               154
             ],
             "pos": [
-              -410,
+              -620,
-              603
+              800
             ]
           },
           {
@@ -204,8 +248,56 @@
               159
             ],
             "pos": [
-              -410,
+              -620,
-              623
+              820
+            ]
+          },
+          {
+            "id": "9f76338b-f4ca-4bb3-b61a-57b3f233061e",
+            "name": "seed",
+            "type": "INT",
+            "linkIds": [
+              377
+            ],
+            "pos": [
+              -620,
+              840
+            ]
+          },
+          {
+            "id": "8d0422d5-5eee-4f7e-9817-dc613cc62eca",
+            "name": "unet_name",
+            "type": "COMBO",
+            "linkIds": [
+              378
+            ],
+            "pos": [
+              -620,
+              860
+            ]
+          },
+          {
+            "id": "552eece2-a735-4d00-ae78-ded454622bc1",
+            "name": "clip_name",
+            "type": "COMBO",
+            "linkIds": [
+              379
+            ],
+            "pos": [
+              -620,
+              880
+            ]
+          },
+          {
+            "id": "1e6d141c-d0f9-4a2b-895c-b6780e57cfa0",
+            "name": "vae_name",
+            "type": "COMBO",
+            "linkIds": [
+              380
+            ],
+            "pos": [
+              -620,
+              900
             ]
           }
         ],
@@ -231,14 +323,14 @@
             "type": "CLIPLoader",
             "pos": [
               -320,
-              310
+              360
             ],
             "size": [
-              346.7470703125,
+              350,
-              106
+              150
             ],
             "flags": {},
-            "order": 0,
+            "order": 5,
             "mode": 0,
             "inputs": [
               {
@@ -248,7 +340,7 @@
                 "widget": {
                   "name": "clip_name"
                 },
-                "link": null
+                "link": 379
               },
               {
                 "localized_name": "type",
@@ -283,9 +375,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "CLIPLoader",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "CLIPLoader",
               "models": [
                 {
                   "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors",
@@ -312,14 +409,14 @@
             "type": "VAELoader",
             "pos": [
               -320,
-              460
+              580
             ],
             "size": [
-              346.7470703125,
+              350,
-              58
+              110
             ],
             "flags": {},
-            "order": 1,
+            "order": 6,
             "mode": 0,
             "inputs": [
               {
@@ -329,7 +426,7 @@
                 "widget": {
                   "name": "vae_name"
                 },
-                "link": null
+                "link": 380
               }
             ],
             "outputs": [
@@ -345,9 +442,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "VAELoader",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "VAELoader",
               "models": [
                 {
                   "name": "qwen_image_layered_vae.safetensors",
@@ -375,11 +477,11 @@
               420
             ],
             "size": [
-              425.27801513671875,
+              430,
-              180.6060791015625
+              190
             ],
             "flags": {},
-            "order": 3,
+            "order": 2,
             "mode": 0,
             "inputs": [
               {
@@ -411,9 +513,14 @@
             ],
             "title": "CLIP Text Encode (Negative Prompt)",
             "properties": {
-              "Node name for S&R": "CLIPTextEncode",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "CLIPTextEncode",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -432,12 +539,12 @@
             "id": 70,
             "type": "ReferenceLatent",
             "pos": [
-              330,
+              140,
-              670
+              700
             ],
             "size": [
-              204.1666717529297,
+              210,
-              46
+              50
             ],
             "flags": {
               "collapsed": true
@@ -470,9 +577,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "ReferenceLatent",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "ReferenceLatent",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -480,19 +592,18 @@
               "secondTabText": "Send Back",
               "secondTabOffset": 80,
               "secondTabWidth": 65
-            },
+            }
-            "widgets_values": []
           },
           {
             "id": 69,
             "type": "ReferenceLatent",
             "pos": [
-              330,
+              160,
-              710
+              820
             ],
             "size": [
-              204.1666717529297,
+              210,
-              46
+              50
             ],
             "flags": {
               "collapsed": true
@@ -525,9 +636,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "ReferenceLatent",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "ReferenceLatent",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -535,8 +651,7 @@
               "secondTabText": "Send Back",
               "secondTabOffset": 80,
               "secondTabWidth": 65
-            },
+            }
-            "widgets_values": []
           },
           {
             "id": 66,
@@ -547,10 +662,10 @@
             ],
             "size": [
               270,
-              58
+              110
             ],
             "flags": {},
-            "order": 4,
+            "order": 7,
             "mode": 0,
             "inputs": [
               {
@@ -580,9 +695,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "ModelSamplingAuraFlow",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "ModelSamplingAuraFlow",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -600,11 +720,11 @@
             "type": "LatentCutToBatch",
             "pos": [
               830,
-              160
+              140
             ],
             "size": [
               270,
-              82
+              140
             ],
             "flags": {},
             "order": 11,
@@ -646,9 +766,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "LatentCutToBatch",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "LatentCutToBatch",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -666,12 +791,12 @@
             "id": 71,
             "type": "VAEEncode",
             "pos": [
-              100,
+              -280,
-              690
+              780
             ],
             "size": [
-              140,
+              230,
-              46
+              100
             ],
             "flags": {
               "collapsed": false
@@ -704,9 +829,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "VAEEncode",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "VAEEncode",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -714,24 +844,23 @@
               "secondTabText": "Send Back",
               "secondTabOffset": 80,
               "secondTabWidth": 65
-            },
+            }
-            "widgets_values": []
           },
           {
             "id": 8,
             "type": "VAEDecode",
             "pos": [
               850,
-              310
+              370
             ],
             "size": [
               210,
-              46
+              50
             ],
             "flags": {
               "collapsed": true
             },
-            "order": 7,
+            "order": 3,
             "mode": 0,
             "inputs": [
               {
@@ -759,9 +888,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "VAEDecode",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "VAEDecode",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -769,8 +903,7 @@
               "secondTabText": "Send Back",
               "secondTabOffset": 80,
               "secondTabWidth": 65
-            },
+            }
-            "widgets_values": []
           },
           {
             "id": 6,
@@ -780,11 +913,11 @@
               180
             ],
             "size": [
-              422.84503173828125,
+              430,
-              164.31304931640625
+              170
             ],
             "flags": {},
-            "order": 6,
+            "order": 1,
             "mode": 0,
             "inputs": [
               {
@@ -816,9 +949,14 @@
             ],
             "title": "CLIP Text Encode (Positive Prompt)",
             "properties": {
-              "Node name for S&R": "CLIPTextEncode",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "CLIPTextEncode",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -838,14 +976,14 @@
             "type": "KSampler",
             "pos": [
               530,
-              280
+              340
             ],
             "size": [
               270,
               400
             ],
             "flags": {},
-            "order": 5,
+            "order": 0,
             "mode": 0,
             "inputs": [
               {
@@ -879,7 +1017,7 @@
                 "widget": {
                   "name": "seed"
                 },
-                "link": null
+                "link": 377
               },
               {
                 "localized_name": "steps",
@@ -939,9 +1077,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "KSampler",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "KSampler",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -964,12 +1107,12 @@
             "id": 78,
             "type": "GetImageSize",
             "pos": [
-              80,
+              -280,
-              790
+              930
             ],
             "size": [
-              210,
+              230,
-              136
+              140
             ],
             "flags": {},
             "order": 12,
@@ -1007,9 +1150,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "GetImageSize",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "GetImageSize",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -1017,23 +1165,23 @@
               "secondTabText": "Send Back",
               "secondTabOffset": 80,
               "secondTabWidth": 65
-            },
+            }
-            "widgets_values": []
           },
           {
             "id": 83,
             "type": "EmptyQwenImageLayeredLatentImage",
             "pos": [
-              320,
+              -280,
-              790
+              1120
             ],
             "size": [
-              330.9341796875,
+              340,
-              130
+              200
             ],
             "flags": {},
             "order": 13,
             "mode": 0,
+            "showAdvanced": true,
             "inputs": [
               {
                 "localized_name": "width",
@@ -1083,9 +1231,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "EmptyQwenImageLayeredLatentImage",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "EmptyQwenImageLayeredLatentImage",
               "enableTabs": false,
               "tabWidth": 65,
               "tabXOffset": 10,
@@ -1109,11 +1262,11 @@
               180
             ],
             "size": [
-              346.7470703125,
+              350,
-              82
+              110
             ],
             "flags": {},
-            "order": 2,
+            "order": 4,
             "mode": 0,
             "inputs": [
               {
@@ -1123,7 +1276,7 @@
                 "widget": {
                   "name": "unet_name"
                 },
-                "link": null
+                "link": 378
               },
               {
                 "localized_name": "weight_dtype",
@@ -1147,9 +1300,14 @@
               }
             ],
             "properties": {
-              "Node name for S&R": "UNETLoader",
               "cnr_id": "comfy-core",
               "ver": "0.5.1",
+              "ue_properties": {
+                "widget_ue_connectable": {},
+                "input_ue_unconnectable": {},
+                "version": "7.7"
+              },
+              "Node name for S&R": "UNETLoader",
               "models": [
                 {
                   "name": "qwen_image_layered_bf16.safetensors",
@@ -1191,8 +1349,8 @@
             "bounding": [
               -330,
               110,
-              366.7470703125,
+              370,
-              421.6
+              610
             ],
             "color": "#3f789e",
             "font_size": 24,
@@ -1391,6 +1549,38 @@
             "target_id": 83,
             "target_slot": 2,
             "type": "INT"
+          },
+          {
+            "id": 377,
+            "origin_id": -10,
+            "origin_slot": 5,
+            "target_id": 3,
+            "target_slot": 4,
+            "type": "INT"
+          },
+          {
+            "id": 378,
+            "origin_id": -10,
+            "origin_slot": 6,
+            "target_id": 37,
+            "target_slot": 0,
+            "type": "COMBO"
+          },
+          {
+            "id": 379,
+            "origin_id": -10,
+            "origin_slot": 7,
+            "target_id": 38,
+            "target_slot": 0,
+            "type": "COMBO"
+          },
+          {
+            "id": 380,
+            "origin_id": -10,
+            "origin_slot": 8,
+            "target_id": 39,
+            "target_slot": 0,
+            "type": "COMBO"
           }
         ],
         "extra": {
@@ -1400,7 +1590,6 @@
       }
     ]
   },
-  "config": {},
   "extra": {
     "ds": {
       "scale": 1.14,
@@ -1409,7 +1598,6 @@
         6.855893974423647
       ]
     },
-    "workflowRendererVersion": "LG"
+    "ue_links": []
-  },
+  }
-  "version": 0.4
+}
-}

comfy/model_patcher.py

@@ -31,6 +31,7 @@ import comfy.float
 import comfy.hooks
 import comfy.lora
 import comfy.model_management
+import comfy.ops
 import comfy.patcher_extension
 import comfy.utils
 from comfy.comfy_types import UnetWrapperFunction
@@ -856,7 +857,9 @@ class ModelPatcher:
                     if m.comfy_patched_weights == True:
                         continue
 
-                for param in params:
+                for param, param_value in params.items():
+                    if hasattr(m, "comfy_cast_weights") and getattr(param_value, "is_meta", False):
+                        comfy.ops.disable_weight_init._zero_init_parameter(m, param)
                     key = key_param_name_to_key(n, param)
                     self.unpin_weight(key)
                     self.patch_weight_to_device(key, device_to=device_to)

comfy/ops.py

@@ -79,14 +79,21 @@ def cast_to_input(weight, input, non_blocking=False, copy=True):
     return comfy.model_management.cast_to(weight, input.dtype, input.device, non_blocking=non_blocking, copy=copy)
 
 
-def cast_bias_weight_with_vbar(s, dtype, device, bias_dtype, non_blocking, compute_dtype, want_requant):
+def materialize_meta_param(s, param_keys):
+    for param_key in param_keys:
+        param = getattr(s, param_key, None)
+        if param is not None and getattr(param, "is_meta", False):
+            setattr(s, param_key, torch.nn.Parameter(torch.zeros(param.shape, dtype=param.dtype), requires_grad=param.requires_grad))
 
+
+def cast_bias_weight_with_vbar(s, dtype, device, bias_dtype, non_blocking, compute_dtype, want_requant):
     #vbar doesn't support CPU weights, but some custom nodes have weird paths
     #that might switch the layer to the CPU and expect it to work. We have to take
     #a clone conservatively as we are mmapped and some SFT files are packed misaligned
     #If you are a custom node author reading this, please move your layer to the GPU
     #or declare your ModelPatcher as CPU in the first place.
     if comfy.model_management.is_device_cpu(device):
+        materialize_meta_param(s, ["weight", "bias"])
         weight = s.weight.to(dtype=dtype, copy=True)
         if isinstance(weight, QuantizedTensor):
             weight = weight.dequantize()
@@ -108,6 +115,7 @@ def cast_bias_weight_with_vbar(s, dtype, device, bias_dtype, non_blocking, compu
             xfer_dest = comfy_aimdo.torch.aimdo_to_tensor(s._v, device)
 
     if not resident:
+        materialize_meta_param(s, ["weight", "bias"])
         cast_geometry = comfy.memory_management.tensors_to_geometries([ s.weight, s.bias ])
         cast_dest = None
 
@@ -306,6 +314,12 @@ class CastWeightBiasOp:
     bias_function = []
 
 class disable_weight_init:
+    @staticmethod
+    def _zero_init_parameter(module, name):
+        param = getattr(module, name)
+        device = None if getattr(param, "is_meta", False) else param.device
+        setattr(module, name, torch.nn.Parameter(torch.zeros(param.shape, device=device, dtype=param.dtype), requires_grad=False))
+
     @staticmethod
     def _lazy_load_from_state_dict(module, state_dict, prefix, local_metadata,
                                    missing_keys, unexpected_keys, weight_shape,

comfy_api/latest/_input_impl/video_types.py

@@ -12,6 +12,7 @@ import numpy as np
 import math
 import torch
 from .._util import VideoContainer, VideoCodec, VideoComponents
+import logging
 
 
 def container_to_output_format(container_format: str | None) -> str | None:
@@ -238,64 +239,107 @@ class VideoFromFile(VideoInput):
             start_time = max(self._get_raw_duration() + self.__start_time, 0)
         else:
             start_time = self.__start_time
+
         # Get video frames
         frames = []
+        audio_frames = []
+        alphas = None
         start_pts = int(start_time / video_stream.time_base)
         end_pts = int((start_time + self.__duration) / video_stream.time_base)
-        container.seek(start_pts, stream=video_stream)
-        for frame in container.decode(video_stream):
-            if frame.pts < start_pts:
-                continue
-            if self.__duration and frame.pts >= end_pts:
-                break
-            img = frame.to_ndarray(format='gbrpf32le')  # shape: (H, W, 3)
-            img = torch.from_numpy(img)
-            frames.append(img)
 
-        images = torch.stack(frames) if len(frames) > 0 else torch.zeros(0, 3, 0, 0)
+        if start_pts != 0:
+            container.seek(start_pts, stream=video_stream)
+
+        image_format = 'gbrpf32le'
+        audio = None
+
+        streams = [video_stream]
+        has_first_audio_frame = False
+        checked_alpha = False
+
+        # Default to False so we decode until EOF if duration is 0
+        video_done = False
+        audio_done = True
+
+        if len(container.streams.audio):
+            audio_stream = container.streams.audio[-1]
+            streams += [audio_stream]
+            resampler = av.audio.resampler.AudioResampler(format='fltp')
+            audio_done = False
+
+        for packet in container.demux(*streams):
+            if video_done and audio_done:
+                break
+
+            if packet.stream.type == "video":
+                if video_done:
+                    continue
+                try:
+                    for frame in packet.decode():
+                        if frame.pts < start_pts:
+                            continue
+                        if self.__duration and frame.pts >= end_pts:
+                            video_done = True
+                            break
+
+                        if not checked_alpha:
+                            for comp in frame.format.components:
+                                if comp.is_alpha:
+                                    alphas = []
+                                    image_format = 'gbrapf32le'
+                                    break
+                            checked_alpha = True
+
+                        img = frame.to_ndarray(format=image_format)  # shape: (H, W, 4)
+                        if alphas is None:
+                            frames.append(torch.from_numpy(img))
+                        else:
+                            frames.append(torch.from_numpy(img[..., :-1]))
+                            alphas.append(torch.from_numpy(img[..., -1:]))
+                except av.error.InvalidDataError:
+                    logging.info("pyav decode error")
+
+            elif packet.stream.type == "audio":
+                if audio_done:
+                    continue
+
+                aframes = itertools.chain.from_iterable(
+                    map(resampler.resample, packet.decode())
+                )
+                for frame in aframes:
+                    if self.__duration and frame.time > start_time + self.__duration:
+                        audio_done = True
+                        break
+
+                    if not has_first_audio_frame:
+                        offset_seconds = start_time - frame.pts * audio_stream.time_base
+                        to_skip = max(0, int(offset_seconds * audio_stream.sample_rate))
+                        if to_skip < frame.samples:
+                            has_first_audio_frame = True
+                            audio_frames.append(frame.to_ndarray()[..., to_skip:])
+                    else:
+                        audio_frames.append(frame.to_ndarray())
+
+        images = torch.stack(frames) if len(frames) > 0 else torch.zeros(0, 0, 0, 3)
+        if alphas is not None:
+            alphas = torch.stack(alphas) if len(alphas) > 0 else torch.zeros(0, 0, 0, 1)
 
         # Get frame rate
         frame_rate = Fraction(video_stream.average_rate) if video_stream.average_rate else Fraction(1)
 
-        # Get audio if available
+        if len(audio_frames) > 0:
-        audio = None
+            audio_data = np.concatenate(audio_frames, axis=1)  # shape: (channels, total_samples)
-        container.seek(start_pts, stream=video_stream)
+            if self.__duration:
-        # Use last stream for consistency
+                audio_data = audio_data[..., :int(self.__duration * audio_stream.sample_rate)]
-        if len(container.streams.audio):
-            audio_stream = container.streams.audio[-1]
-            audio_frames = []
-            resample = av.audio.resampler.AudioResampler(format='fltp').resample
-            frames = itertools.chain.from_iterable(
-                map(resample, container.decode(audio_stream))
-            )
 
-            has_first_frame = False
+            audio_tensor = torch.from_numpy(audio_data).unsqueeze(0)  # shape: (1, channels, total_samples)
-            for frame in frames:
+            audio = AudioInput({
-                offset_seconds = start_time - frame.pts * audio_stream.time_base
+                "waveform": audio_tensor,
-                to_skip = max(0, int(offset_seconds * audio_stream.sample_rate))
+                "sample_rate": int(audio_stream.sample_rate) if audio_stream.sample_rate else 1,
-                if to_skip < frame.samples:
+            })
-                    has_first_frame = True
-                    break
-            if has_first_frame:
-                audio_frames.append(frame.to_ndarray()[..., to_skip:])
-
-            for frame in frames:
-                if self.__duration and frame.time > start_time + self.__duration:
-                    break
-                audio_frames.append(frame.to_ndarray())  # shape: (channels, samples)
-            if len(audio_frames) > 0:
-                audio_data = np.concatenate(audio_frames, axis=1)  # shape: (channels, total_samples)
-                if self.__duration:
-                    audio_data = audio_data[..., :int(self.__duration * audio_stream.sample_rate)]
-
-                audio_tensor = torch.from_numpy(audio_data).unsqueeze(0)  # shape: (1, channels, total_samples)
-                audio = AudioInput({
-                    "waveform": audio_tensor,
-                    "sample_rate": int(audio_stream.sample_rate) if audio_stream.sample_rate else 1,
-                })
 
         metadata = container.metadata
-        return VideoComponents(images=images, audio=audio, frame_rate=frame_rate, metadata=metadata)
+        return VideoComponents(images=images, alpha=alphas, audio=audio, frame_rate=frame_rate, metadata=metadata)
 
     def get_components(self) -> VideoComponents:
         if isinstance(self.__file, io.BytesIO):

comfy_api/latest/_util/video_types.py

@@ -3,7 +3,7 @@ from dataclasses import dataclass
 from enum import Enum
 from fractions import Fraction
 from typing import Optional
-from .._input import ImageInput, AudioInput
+from .._input import ImageInput, AudioInput, MaskInput
 
 class VideoCodec(str, Enum):
     AUTO = "auto"
@@ -48,5 +48,4 @@ class VideoComponents:
     frame_rate: Fraction
     audio: Optional[AudioInput] = None
     metadata: Optional[dict] = None
-
+    alpha: Optional[MaskInput] = None
-

comfy_api_nodes/apis/wan.py

@@ -118,7 +118,7 @@ class Wan27ReferenceVideoInputField(BaseModel):
 class Wan27ReferenceVideoParametersField(BaseModel):
     resolution: str = Field(...)
     ratio: str | None = Field(None)
-    duration: int = Field(5, ge=2, le=10)
+    duration: int = Field(5, ge=2, le=15)
     watermark: bool = Field(False)
     seed: int = Field(..., ge=0, le=2147483647)
 
@@ -157,7 +157,7 @@ class Wan27VideoEditInputField(BaseModel):
 class Wan27VideoEditParametersField(BaseModel):
     resolution: str = Field(...)
     ratio: str | None = Field(None)
-    duration: int = Field(0)
+    duration: int | None = Field(0)
     audio_setting: str = Field("auto")
     watermark: bool = Field(False)
     seed: int = Field(..., ge=0, le=2147483647)

comfy_api_nodes/nodes_wan.py

@@ -1646,6 +1646,557 @@ class Wan2ReferenceVideoApi(IO.ComfyNode):
         return IO.NodeOutput(await download_url_to_video_output(response.output.video_url))
 
 
+class HappyHorseTextToVideoApi(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="HappyHorseTextToVideoApi",
+            display_name="HappyHorse Text to Video",
+            category="api node/video/Wan",
+            description="Generates a video based on a text prompt using the HappyHorse model.",
+            inputs=[
+                IO.DynamicCombo.Input(
+                    "model",
+                    options=[
+                        IO.DynamicCombo.Option(
+                            "happyhorse-1.0-t2v",
+                            [
+                                IO.String.Input(
+                                    "prompt",
+                                    multiline=True,
+                                    default="",
+                                    tooltip="Prompt describing the elements and visual features. "
+                                    "Supports English and Chinese.",
+                                ),
+                                IO.Combo.Input(
+                                    "resolution",
+                                    options=["720P", "1080P"],
+                                ),
+                                IO.Combo.Input(
+                                    "ratio",
+                                    options=["16:9", "9:16", "1:1", "4:3", "3:4"],
+                                ),
+                                IO.Int.Input(
+                                    "duration",
+                                    default=5,
+                                    min=3,
+                                    max=15,
+                                    step=1,
+                                    display_mode=IO.NumberDisplay.number,
+                                ),
+                            ],
+                        ),
+                    ],
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    step=1,
+                    display_mode=IO.NumberDisplay.number,
+                    control_after_generate=True,
+                    tooltip="Seed to use for generation.",
+                ),
+                IO.Boolean.Input(
+                    "watermark",
+                    default=False,
+                    tooltip="Whether to add an AI-generated watermark to the result.",
+                    advanced=True,
+                ),
+            ],
+            outputs=[
+                IO.Video.Output(),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]),
+                expr="""
+                (
+                  $res := $lookup(widgets, "model.resolution");
+                  $dur := $lookup(widgets, "model.duration");
+                  $ppsTable := { "720p": 0.14, "1080p": 0.24 };
+                  $pps := $lookup($ppsTable, $res);
+                  { "type": "usd", "usd": $pps * $dur }
+                )
+                """,
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        model: dict,
+        seed: int,
+        watermark: bool,
+    ):
+        validate_string(model["prompt"], strip_whitespace=False, min_length=1)
+        initial_response = await sync_op(
+            cls,
+            ApiEndpoint(
+                path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis",
+                method="POST",
+            ),
+            response_model=TaskCreationResponse,
+            data=Wan27Text2VideoTaskCreationRequest(
+                model=model["model"],
+                input=Text2VideoInputField(
+                    prompt=model["prompt"],
+                    negative_prompt=None,
+                ),
+                parameters=Wan27Text2VideoParametersField(
+                    resolution=model["resolution"],
+                    ratio=model["ratio"],
+                    duration=model["duration"],
+                    seed=seed,
+                    watermark=watermark,
+                ),
+            ),
+        )
+        if not initial_response.output:
+            raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}")
+        response = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
+            response_model=VideoTaskStatusResponse,
+            status_extractor=lambda x: x.output.task_status,
+            poll_interval=7,
+        )
+        return IO.NodeOutput(await download_url_to_video_output(response.output.video_url))
+
+
+class HappyHorseImageToVideoApi(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="HappyHorseImageToVideoApi",
+            display_name="HappyHorse Image to Video",
+            category="api node/video/Wan",
+            description="Generate a video from a first-frame image using the HappyHorse model.",
+            inputs=[
+                IO.DynamicCombo.Input(
+                    "model",
+                    options=[
+                        IO.DynamicCombo.Option(
+                            "happyhorse-1.0-i2v",
+                            [
+                                IO.String.Input(
+                                    "prompt",
+                                    multiline=True,
+                                    default="",
+                                    tooltip="Prompt describing the elements and visual features. "
+                                    "Supports English and Chinese.",
+                                ),
+                                IO.Combo.Input(
+                                    "resolution",
+                                    options=["720P", "1080P"],
+                                ),
+                                IO.Int.Input(
+                                    "duration",
+                                    default=5,
+                                    min=3,
+                                    max=15,
+                                    step=1,
+                                    display_mode=IO.NumberDisplay.number,
+                                ),
+                            ],
+                        ),
+                    ],
+                ),
+                IO.Image.Input(
+                    "first_frame",
+                    tooltip="First frame image. The output aspect ratio is derived from this image.",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    step=1,
+                    display_mode=IO.NumberDisplay.number,
+                    control_after_generate=True,
+                    tooltip="Seed to use for generation.",
+                ),
+                IO.Boolean.Input(
+                    "watermark",
+                    default=False,
+                    tooltip="Whether to add an AI-generated watermark to the result.",
+                    advanced=True,
+                ),
+            ],
+            outputs=[
+                IO.Video.Output(),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]),
+                expr="""
+                (
+                  $res := $lookup(widgets, "model.resolution");
+                  $dur := $lookup(widgets, "model.duration");
+                  $ppsTable := { "720p": 0.14, "1080p": 0.24 };
+                  $pps := $lookup($ppsTable, $res);
+                  { "type": "usd", "usd": $pps * $dur }
+                )
+                """,
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        model: dict,
+        first_frame: Input.Image,
+        seed: int,
+        watermark: bool,
+    ):
+        media = [
+            Wan27MediaItem(
+                type="first_frame",
+                url=await upload_image_to_comfyapi(cls, image=first_frame),
+            )
+        ]
+        initial_response = await sync_op(
+            cls,
+            ApiEndpoint(
+                path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis",
+                method="POST",
+            ),
+            response_model=TaskCreationResponse,
+            data=Wan27ImageToVideoTaskCreationRequest(
+                model=model["model"],
+                input=Wan27ImageToVideoInputField(
+                    prompt=model["prompt"] or None,
+                    negative_prompt=None,
+                    media=media,
+                ),
+                parameters=Wan27ImageToVideoParametersField(
+                    resolution=model["resolution"],
+                    duration=model["duration"],
+                    seed=seed,
+                    watermark=watermark,
+                ),
+            ),
+        )
+        if not initial_response.output:
+            raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}")
+        response = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
+            response_model=VideoTaskStatusResponse,
+            status_extractor=lambda x: x.output.task_status,
+            poll_interval=7,
+        )
+        return IO.NodeOutput(await download_url_to_video_output(response.output.video_url))
+
+
+class HappyHorseVideoEditApi(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="HappyHorseVideoEditApi",
+            display_name="HappyHorse Video Edit",
+            category="api node/video/Wan",
+            description="Edit a video using text instructions or reference images with the HappyHorse model. "
+            "Output duration is 3-15s and matches the input video; inputs longer than 15s are truncated.",
+            inputs=[
+                IO.DynamicCombo.Input(
+                    "model",
+                    options=[
+                        IO.DynamicCombo.Option(
+                            "happyhorse-1.0-video-edit",
+                            [
+                                IO.String.Input(
+                                    "prompt",
+                                    multiline=True,
+                                    default="",
+                                    tooltip="Editing instructions or style transfer requirements.",
+                                ),
+                                IO.Combo.Input(
+                                    "resolution",
+                                    options=["720P", "1080P"],
+                                ),
+                                IO.Combo.Input(
+                                    "ratio",
+                                    options=["16:9", "9:16", "1:1", "4:3", "3:4"],
+                                    tooltip="Aspect ratio. If not changed, approximates the input video ratio.",
+                                ),
+                                IO.Autogrow.Input(
+                                    "reference_images",
+                                    template=IO.Autogrow.TemplateNames(
+                                        IO.Image.Input("reference_image"),
+                                        names=[
+                                            "image1",
+                                            "image2",
+                                            "image3",
+                                            "image4",
+                                            "image5",
+                                        ],
+                                        min=0,
+                                    ),
+                                ),
+                            ],
+                        ),
+                    ],
+                ),
+                IO.Video.Input(
+                    "video",
+                    tooltip="The video to edit.",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    step=1,
+                    display_mode=IO.NumberDisplay.number,
+                    control_after_generate=True,
+                    tooltip="Seed to use for generation.",
+                ),
+                IO.Boolean.Input(
+                    "watermark",
+                    default=False,
+                    tooltip="Whether to add an AI-generated watermark to the result.",
+                    advanced=True,
+                ),
+            ],
+            outputs=[
+                IO.Video.Output(),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution"]),
+                expr="""
+                (
+                  $res := $lookup(widgets, "model.resolution");
+                  $ppsTable := { "720p": 0.14, "1080p": 0.24 };
+                  $pps := $lookup($ppsTable, $res);
+                  { "type": "usd", "usd": $pps, "format": { "suffix": "/second" } }
+                )
+                """,
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        model: dict,
+        video: Input.Video,
+        seed: int,
+        watermark: bool,
+    ):
+        validate_string(model["prompt"], strip_whitespace=False, min_length=1)
+        validate_video_duration(video, min_duration=3, max_duration=60)
+        media = [Wan27MediaItem(type="video", url=await upload_video_to_comfyapi(cls, video))]
+        reference_images = model.get("reference_images", {})
+        for key in reference_images:
+            media.append(
+                Wan27MediaItem(
+                    type="reference_image", url=await upload_image_to_comfyapi(cls, image=reference_images[key])
+                )
+            )
+        initial_response = await sync_op(
+            cls,
+            ApiEndpoint(
+                path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis",
+                method="POST",
+            ),
+            response_model=TaskCreationResponse,
+            data=Wan27VideoEditTaskCreationRequest(
+                model=model["model"],
+                input=Wan27VideoEditInputField(prompt=model["prompt"], media=media),
+                parameters=Wan27VideoEditParametersField(
+                    resolution=model["resolution"],
+                    ratio=model["ratio"],
+                    duration=None,
+                    watermark=watermark,
+                    seed=seed,
+                ),
+            ),
+        )
+        if not initial_response.output:
+            raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}")
+        response = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
+            response_model=VideoTaskStatusResponse,
+            status_extractor=lambda x: x.output.task_status,
+            poll_interval=7,
+        )
+        return IO.NodeOutput(await download_url_to_video_output(response.output.video_url))
+
+
+class HappyHorseReferenceVideoApi(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="HappyHorseReferenceVideoApi",
+            display_name="HappyHorse Reference to Video",
+            category="api node/video/Wan",
+            description="Generate a video featuring a person or object from reference materials with the HappyHorse "
+            "model. Supports single-character performances and multi-character interactions.",
+            inputs=[
+                IO.DynamicCombo.Input(
+                    "model",
+                    options=[
+                        IO.DynamicCombo.Option(
+                            "happyhorse-1.0-r2v",
+                            [
+                                IO.String.Input(
+                                    "prompt",
+                                    multiline=True,
+                                    default="",
+                                    tooltip="Prompt describing the video. Use identifiers such as 'character1' and "
+                                    "'character2' to refer to the reference characters.",
+                                ),
+                                IO.Combo.Input(
+                                    "resolution",
+                                    options=["720P", "1080P"],
+                                ),
+                                IO.Combo.Input(
+                                    "ratio",
+                                    options=["16:9", "9:16", "1:1", "4:3", "3:4"],
+                                ),
+                                IO.Int.Input(
+                                    "duration",
+                                    default=5,
+                                    min=3,
+                                    max=15,
+                                    step=1,
+                                    display_mode=IO.NumberDisplay.number,
+                                ),
+                                IO.Autogrow.Input(
+                                    "reference_images",
+                                    template=IO.Autogrow.TemplateNames(
+                                        IO.Image.Input("reference_image"),
+                                        names=[
+                                            "image1",
+                                            "image2",
+                                            "image3",
+                                            "image4",
+                                            "image5",
+                                            "image6",
+                                            "image7",
+                                            "image8",
+                                            "image9",
+                                        ],
+                                        min=1,
+                                    ),
+                                ),
+                            ],
+                        ),
+                    ],
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    step=1,
+                    display_mode=IO.NumberDisplay.number,
+                    control_after_generate=True,
+                    tooltip="Seed to use for generation.",
+                ),
+                IO.Boolean.Input(
+                    "watermark",
+                    default=False,
+                    tooltip="Whether to add an AI-generated watermark to the result.",
+                    advanced=True,
+                ),
+            ],
+            outputs=[
+                IO.Video.Output(),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution", "model.duration"]),
+                expr="""
+                (
+                  $res := $lookup(widgets, "model.resolution");
+                  $dur := $lookup(widgets, "model.duration");
+                  $ppsTable := { "720p": 0.14, "1080p": 0.24 };
+                  $pps := $lookup($ppsTable, $res);
+                  { "type": "usd", "usd": $pps * $dur }
+                )
+                """,
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        model: dict,
+        seed: int,
+        watermark: bool,
+    ):
+        validate_string(model["prompt"], strip_whitespace=False, min_length=1)
+        media = []
+        reference_images = model.get("reference_images", {})
+        for key in reference_images:
+            media.append(
+                Wan27MediaItem(
+                    type="reference_image",
+                    url=await upload_image_to_comfyapi(cls, image=reference_images[key]),
+                )
+            )
+        if not media:
+            raise ValueError("At least one reference reference image must be provided.")
+
+        initial_response = await sync_op(
+            cls,
+            ApiEndpoint(
+                path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis",
+                method="POST",
+            ),
+            response_model=TaskCreationResponse,
+            data=Wan27ReferenceVideoTaskCreationRequest(
+                model=model["model"],
+                input=Wan27ReferenceVideoInputField(
+                    prompt=model["prompt"],
+                    negative_prompt=None,
+                    media=media,
+                ),
+                parameters=Wan27ReferenceVideoParametersField(
+                    resolution=model["resolution"],
+                    ratio=model["ratio"],
+                    duration=model["duration"],
+                    watermark=watermark,
+                    seed=seed,
+                ),
+            ),
+        )
+        if not initial_response.output:
+            raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}")
+        response = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
+            response_model=VideoTaskStatusResponse,
+            status_extractor=lambda x: x.output.task_status,
+            poll_interval=7,
+        )
+        return IO.NodeOutput(await download_url_to_video_output(response.output.video_url))
+
+
 class WanApiExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@@ -1660,6 +2211,10 @@ class WanApiExtension(ComfyExtension):
             Wan2VideoContinuationApi,
             Wan2VideoEditApi,
             Wan2ReferenceVideoApi,
+            HappyHorseTextToVideoApi,
+            HappyHorseImageToVideoApi,
+            HappyHorseVideoEditApi,
+            HappyHorseReferenceVideoApi,
         ]
 
 

comfy_extras/nodes_hunyuan3d.py

@@ -637,7 +637,7 @@ class SaveGLB(IO.ComfyNode):
                     ],
                     tooltip="Mesh or 3D file to save",
                 ),
-                IO.String.Input("filename_prefix", default="mesh/ComfyUI"),
+                IO.String.Input("filename_prefix", default="3d/ComfyUI"),
             ],
             hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo]
         )

comfy_extras/nodes_mask.py

@@ -2,6 +2,7 @@ import numpy as np
 import scipy.ndimage
 import torch
 import comfy.utils
+import comfy.model_management
 import node_helpers
 from typing_extensions import override
 from comfy_api.latest import ComfyExtension, IO, UI
@@ -188,7 +189,7 @@ class SolidMask(IO.ComfyNode):
 
     @classmethod
     def execute(cls, value, width, height) -> IO.NodeOutput:
-        out = torch.full((1, height, width), value, dtype=torch.float32, device="cpu")
+        out = torch.full((1, height, width), value, dtype=torch.float32, device=comfy.model_management.intermediate_device())
         return IO.NodeOutput(out)
 
     solid = execute  # TODO: remove
@@ -262,6 +263,7 @@ class MaskComposite(IO.ComfyNode):
     def execute(cls, destination, source, x, y, operation) -> IO.NodeOutput:
         output = destination.reshape((-1, destination.shape[-2], destination.shape[-1])).clone()
         source = source.reshape((-1, source.shape[-2], source.shape[-1]))
+        source = source.to(output.device)
 
         left, top = (x, y,)
         right, bottom = (min(left + source.shape[-1], destination.shape[-1]), min(top + source.shape[-2], destination.shape[-2]))

comfy_extras/nodes_sd3.py

@@ -54,7 +54,7 @@ class EmptySD3LatentImage(io.ComfyNode):
 
     @classmethod
     def execute(cls, width, height, batch_size=1) -> io.NodeOutput:
-        latent = torch.zeros([batch_size, 16, height // 8, width // 8], device=comfy.model_management.intermediate_device())
+        latent = torch.zeros([batch_size, 16, height // 8, width // 8], device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())
         return io.NodeOutput({"samples": latent, "downscale_ratio_spacial": 8})
 
     generate = execute  # TODO: remove

comfyui_version.py

@@ -1,3 +1,3 @@
 # This file is automatically generated by the build process when version is
 # updated in pyproject.toml.
-__version__ = "0.19.3"
+__version__ = "0.20.1"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ComfyUI"
-version = "0.19.3"
+version = "0.20.1"
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.10"

requirements.txt

@@ -1,5 +1,5 @@
 comfyui-frontend-package==1.42.15
-comfyui-workflow-templates==0.9.62
+comfyui-workflow-templates==0.9.63
 comfyui-embedded-docs==0.4.4
 torch
 torchsde