blueprints: add subgraph descriptions for previously undocumented workflows

Fill missing definitions.subgraphs[].description across ERNIE, Flux.2,
Z-Image base/default, Qwen edit 2509, Wan I2V, SAM3 image/video,
and align wording with existing blueprint style.

Co-authored-by: Cursor <cursoragent@cursor.com>

blueprints/ControlNet (Z-Image-Turbo).json

@@ -1401,7 +1401,8 @@
         "extra": {
           "workflowRendererVersion": "LG"
         },
-        "category": "Image generation and editing/ControlNet"
+        "category": "Image generation and editing/ControlNet",
+        "description": "Generates images from a text prompt and ControlNet conditioning (e.g. depth, canny) using Z-Image-Turbo."
       }
     ]
   },

blueprints/First-Last-Frame to Video.json

@@ -3350,7 +3350,8 @@
           }
         ],
         "extra": {},
-        "category": "Video generation and editing/First-Last-Frame to Video"
+        "category": "Video generation and editing/First-Last-Frame to Video",
+        "description": "Generates a video that interpolates between the first and last keyframes using LTX-2.3, including optional audio."
       }
     ]
   },

blueprints/Frame Interpolation.json

@@ -849,7 +849,8 @@
           }
         ],
         "extra": {},
-        "category": "Video Tools"
+        "category": "Video Tools",
+        "description": "Increases video frame rate by synthesizing intermediate frames with a frame interpolation model."
       }
     ]
   },

blueprints/Get Any Video Frame.json

@@ -467,7 +467,8 @@
           }
         ],
         "extra": {},
-        "category": "Video Tools"
+        "category": "Video Tools",
+        "description": "Extracts one image frame from a video at a chosen index, with optional trim and FPS control."
       }
     ]
   },

blueprints/Image Edit (Flux.2 Dev).json

@@ -2049,7 +2049,8 @@
         "extra": {
           "workflowRendererVersion": "LG"
         },
-        "category": "Image generation and editing/Edit image"
+        "category": "Image generation and editing/Edit image",
+        "description": "Edits an image from text instructions using Flux.2 [dev], with guidance, schedulers, and optional Turbo LoRAs."
       }
     ]
   },

blueprints/Image Edit (Qwen 2509).json

@@ -1938,9 +1938,10 @@
         "extra": {
           "workflowRendererVersion": "LG"
         },
-        "category": "Image generation and editing/Edit image"
+        "category": "Image generation and editing/Edit image",
+        "description": "Edits images from text instructions using Qwen-Image-Edit-2509 with optional Lightning LoRA for few-step sampling."
       }
     ]
   },
   "extra": {}
-}
+}

blueprints/Image Segmentation (SAM3).json

@@ -703,11 +703,12 @@
           }
         ],
         "extra": {},
-        "category": "Image Tools/Image Segmentation"
+        "category": "Image Tools/Image Segmentation",
+        "description": "Segments images into masks using Meta SAM3 from text prompts, points, or boxes."
       }
     ]
   },
   "extra": {
     "ue_links": []
   }
-}
+}

blueprints/Image to Video.json

@@ -1711,7 +1711,8 @@
         "extra": {
           "workflowRendererVersion": "LG"
         },
-        "category": "Video generation and editing/Image to video"
+        "category": "Video generation and editing/Image to video",
+        "description": "Generates video from a starting image and text prompt using Wan 2.2 image-to-video."
       }
     ]
   },
@@ -1732,4 +1733,4 @@
     }
   },
   "version": 0.4
-}
+}

blueprints/Text to Image (Ernie Image Turbo).json

@@ -2101,11 +2101,12 @@
           }
         ],
         "extra": {},
-        "category": "Image generation and editing/Text to image"
+        "category": "Image generation and editing/Text to image",
+        "description": "Generates images from text prompts using ERNIE Image Turbo with bundled encoders and VAE."
       }
     ]
   },
   "extra": {
     "ue_links": []
   }
-}
+}

blueprints/Text to Image (Ernie Image).json

@@ -2179,11 +2179,12 @@
           }
         ],
         "extra": {},
-        "category": "Image generation and editing/Text to image"
+        "category": "Image generation and editing/Text to image",
+        "description": "Generates images from text prompts using ERNIE Image with bundled encoders and VAE."
       }
     ]
   },
   "extra": {
     "ue_links": []
   }
-}
+}

blueprints/Text to Image (Flux.2 Dev).json

@@ -1859,11 +1859,12 @@
         "extra": {
           "workflowRendererVersion": "LG"
         },
-        "category": "Image generation and editing/Text to image"
+        "category": "Image generation and editing/Text to image",
+        "description": "Generates images from text prompts using Flux.2 [dev], Black Forest Labs' Flux.2 diffusion stack."
       }
     ]
   },
   "extra": {
     "ue_links": []
   }
-}
+}

blueprints/Text to Image(Z-Image-Base).json

@@ -1178,9 +1178,10 @@
         "extra": {
           "workflowRendererVersion": "LG"
         },
-        "category": "Image generation and editing/Text to image"
+        "category": "Image generation and editing/Text to image",
+        "description": "Generates images from text prompts using Z-Image base weights with Qwen3 text encoder and bundled VAE."
       }
     ]
   },
   "extra": {}
-}
+}

blueprints/Text to Image.json

@@ -1123,9 +1123,10 @@
         "extra": {
           "workflowRendererVersion": "LG"
         },
-        "category": "Image generation and editing/Text to image"
+        "category": "Image generation and editing/Text to image",
+        "description": "Generates images from text prompts using Z-Image-Turbo defaults with Qwen3 text encoder and VAE."
       }
     ]
   },
   "extra": {}
-}
+}

blueprints/Video Segmentation (SAM3).json

@@ -818,9 +818,10 @@
           }
         ],
         "extra": {},
-        "category": "Video Tools"
+        "category": "Video Tools",
+        "description": "Segments video into temporally consistent masks using Meta SAM3 from text or interactive prompts."
       }
     ]
   },
   "extra": {}
-}
+}