Refine description

blueprints/Depth to Video (ltx 2.0).json

@@ -4234,7 +4234,7 @@
           "workflowRendererVersion": "LG"
         },
         "category": "Video generation and editing/Depth to video",
-        "description": "Generates video from depth maps using LTX-2, with optional synchronized audio."
+        "description": "Generates depth-controlled video with LTX-2: motion and structure follow a depth-reference video alongside text prompting, optional first-frame image conditioning, with optional synchronized audio."
       },
       {
         "id": "38b60539-50a7-42f9-a5fe-bdeca26272e2",

blueprints/Image to Video (Wan 2.2).json

@@ -2028,7 +2028,7 @@
           "workflowRendererVersion": "LG"
         },
         "category": "Video generation and editing/Image to video",
-        "description": "Generates video from an image and text prompt using Wan 2.2, supporting T2V and I2V."
+        "description": "Image-to-video with Wan 2.2 using a start image plus text prompt to extend motion from the still frame."
       }
     ]
   },

blueprints/Remove Background (BiRefNet).json

@@ -74,6 +74,7 @@
         "revision": 0,
         "config": {},
         "name": "Remove Background (BiRefNet)",
+        "description": "Removes or replaces image backgrounds using BiRefNet segmentation and alpha compositing.",
         "inputNode": {
           "id": -10,
           "bounding": [

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

@@ -2102,7 +2102,7 @@
         ],
         "extra": {},
         "category": "Image generation and editing/Text to image",
-        "description": "Generates images from text prompts using ERNIE Image Turbo with bundled encoders and VAE."
+        "description": "Faster ERNIE Image Turbo variant (~8B DiT, distilled for fewer sampling steps): same strengths in Chinese/English on-image text and layout-heavy graphics as the base ERNIE Image lineup, with bundled encoders and VAE."
       }
     ]
   },

blueprints/Text to Image (Ernie Image).json

@@ -2180,7 +2180,7 @@
         ],
         "extra": {},
         "category": "Image generation and editing/Text to image",
-        "description": "Generates images from text prompts using ERNIE Image with bundled encoders and VAE."
+        "description": "Generates images from text prompts using Baidu’s open ERNIE Image (~8B DiT): bilingual in-image typography and layouts (posters, infographics, multi-panel compositions) alongside general scenes, with bundled encoders and VAE."
       }
     ]
   },

blueprints/Text to Image (Flux.1 Dev).json

@@ -1030,7 +1030,7 @@
           "workflowRendererVersion": "LG"
         },
         "category": "Image generation and editing/Text to image",
-        "description": "Generates images from text prompts using Flux.1 [dev], Black Forest Labs' 12B diffusion model."
+        "description": "Generates images from prompts using FLUX.1 [dev]: a 12B rectified-flow MMDiT with dual CLIP plus T5-XXL text encoders and guidance-distilled sampling for sharp prompt following versus classic DDPM diffusion."
       }
     ]
   },

blueprints/Text to Image (Flux.1 Krea Dev).json

@@ -1024,7 +1024,7 @@
           "workflowRendererVersion": "LG"
         },
         "category": "Image generation and editing/Text to image",
-        "description": "Generates images from text prompts using Flux.1 Krea Dev, a Black Forest Labs × Krea collaboration variant."
+        "description": "FLUX.1 Krea [dev] (Black Forest Labs × Krea): open-weight 12B rectified-flow text-to-image drop-in alongside FLUX.1 [dev], tuned away from overcooked saturation toward more natural diversity in people, realism, and style while keeping ecosystem compatibility."
       }
     ]
   },

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

@@ -1860,7 +1860,7 @@
           "workflowRendererVersion": "LG"
         },
         "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."
+        "description": "Generates images from prompts using FLUX.2 [dev]: a newer 32B rectified-flow stack with distilled guidance plus a stronger long-context multimodal encoder for complex scenes, sharper typography/UI text, anatomy, lighting, and high-resolution latent decoding."
       }
     ]
   },