Initial commit: ComfyUI-EnglishAnnotator

2026-05-20 13:01:58 +08:00
commit c81663f9a2
14 changed files with 1078 additions and 0 deletions
@@ -0,0 +1,84 @@
+{
+  "loader": {
+    "class_type": "CheckpointLoaderSimple",
+    "inputs": { "ckpt_name": "sd_xl_base_1.0.safetensors" }
+  },
+  "pos": {
+    "class_type": "CLIPTextEncode",
+    "inputs": {
+      "text": "flat vector illustration of a tidy classroom: wooden desk, chair, blackboard, world map, books, pencil, eraser, backpack, clock, globe, computer, calendar, isometric, bright colors, every object clearly separated, soft daylight",
+      "clip": ["loader", 1]
+    }
+  },
+  "neg": {
+    "class_type": "CLIPTextEncode",
+    "inputs": {
+      "text": "blurry, low quality, watermark, text overlay",
+      "clip": ["loader", 1]
+    }
+  },
+  "latent": {
+    "class_type": "EmptySD3LatentImage",
+    "inputs": { "width": 1024, "height": 1024, "batch_size": 1 }
+  },
+  "sampler": {
+    "class_type": "KSampler",
+    "inputs": {
+      "model": ["loader", 0],
+      "seed": 42,
+      "steps": 25,
+      "cfg": 6.0,
+      "sampler_name": "euler",
+      "scheduler": "simple",
+      "denoise": 1.0,
+      "positive": ["pos", 0],
+      "negative": ["neg", 0],
+      "latent_image": ["latent", 0]
+    }
+  },
+  "decode": {
+    "class_type": "VAEDecode",
+    "inputs": { "samples": ["sampler", 0], "vae": ["loader", 2] }
+  },
+  "f2_load": {
+    "class_type": "Florence2ModelLoader",
+    "inputs": {
+      "model": "microsoft/Florence-2-large",
+      "precision": "fp16",
+      "attention": "sdpa"
+    }
+  },
+  "f2_run": {
+    "class_type": "Florence2Run",
+    "inputs": {
+      "image": ["decode", 0],
+      "florence2_model": ["f2_load", 0],
+      "task": "caption_to_phrase_grounding",
+      "text_input": "desk, chair, blackboard, books, pencil, backpack, clock, globe, computer",
+      "fill_mask": false,
+      "keep_model_loaded": true,
+      "max_new_tokens": 1024,
+      "num_beams": 3,
+      "do_sample": false,
+      "output_mask_select": ""
+    }
+  },
+  "annotate": {
+    "class_type": "EnglishWordAnnotator",
+    "inputs": {
+      "image": ["decode", 0],
+      "bboxes": ["f2_run", 2],
+      "labels": ["f2_run", 3],
+      "font_size": 36,
+      "box_width": 4,
+      "label_position": "above"
+    }
+  },
+  "save": {
+    "class_type": "SaveImage",
+    "inputs": {
+      "images": ["annotate", 0],
+      "filename_prefix": "english_card"
+    }
+  }
+}