docs: add example workflow

- Add workflows/zimage_i2l_example_api.json as API workflow example
- Update README with example workflow section

README.md

@@ -99,6 +99,18 @@ set MODELSCOPE_CACHE=D:\models\modelscope
 3. Use **ZImageI2L Saver** to save the generated LoRA
 4. Use the generated LoRA with any standard LoRA loader node
 
+### Example Workflow
+
+An example API workflow is provided in the `workflows` folder:
+
+- [`workflows/zimage_i2l_example_api.json`](workflows/zimage_i2l_example_api.json) - Complete workflow demonstrating LoRA generation and usage
+
+This workflow includes:
+- Loading reference images (4 images)
+- Generating LoRA with ZImageI2L nodes
+- Applying the generated LoRA to Z-Image model
+- Generating images with the personalized LoRA
+
 ## 📝 Parameters
 
 ### ZImageI2L LoRA Generator

workflows/zimage_i2l_example_api.json

@@ -0,0 +1,287 @@
+{
+  "1": {
+    "inputs": {
+      "unet_name": "z_image_bf16.safetensors",
+      "weight_dtype": "default"
+    },
+    "class_type": "UNETLoader",
+    "_meta": {
+      "title": "Load Diffusion Model"
+    }
+  },
+  "2": {
+    "inputs": {
+      "seed": 392301893067137,
+      "steps": 50,
+      "cfg": 4,
+      "sampler_name": "res_multistep",
+      "scheduler": "simple",
+      "denoise": 1,
+      "model": [
+        "3",
+        0
+      ],
+      "positive": [
+        "5",
+        0
+      ],
+      "negative": [
+        "6",
+        0
+      ],
+      "latent_image": [
+        "11",
+        0
+      ]
+    },
+    "class_type": "KSampler",
+    "_meta": {
+      "title": "KSampler"
+    }
+  },
+  "3": {
+    "inputs": {
+      "shift": 8.000000000000002,
+      "model": [
+        "16",
+        0
+      ]
+    },
+    "class_type": "ModelSamplingAuraFlow",
+    "_meta": {
+      "title": "ModelSamplingAuraFlow"
+    }
+  },
+  "4": {
+    "inputs": {
+      "clip_name": "qwen_3_4b.safetensors",
+      "type": "lumina2",
+      "device": "default"
+    },
+    "class_type": "CLIPLoader",
+    "_meta": {
+      "title": "Load CLIP"
+    }
+  },
+  "5": {
+    "inputs": {
+      "text": "a cat",
+      "clip": [
+        "16",
+        1
+      ]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": {
+      "title": "CLIP Text Encode (Prompt)"
+    }
+  },
+  "6": {
+    "inputs": {
+      "text": "",
+      "clip": [
+        "4",
+        0
+      ]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": {
+      "title": "CLIP Text Encode (Prompt)"
+    }
+  },
+  "7": {
+    "inputs": {
+      "vae_name": "ae.safetensors"
+    },
+    "class_type": "VAELoader",
+    "_meta": {
+      "title": "Load VAE"
+    }
+  },
+  "8": {
+    "inputs": {
+      "samples": [
+        "2",
+        0
+      ],
+      "vae": [
+        "7",
+        0
+      ]
+    },
+    "class_type": "VAEDecode",
+    "_meta": {
+      "title": "VAE Decode"
+    }
+  },
+  "10": {
+    "inputs": {
+      "filename_prefix": "ComfyUI",
+      "images": [
+        "8",
+        0
+      ]
+    },
+    "class_type": "SaveImage",
+    "_meta": {
+      "title": "Save Image"
+    }
+  },
+  "11": {
+    "inputs": {
+      "width": 1024,
+      "height": 1536,
+      "batch_size": 1
+    },
+    "class_type": "EmptySD3LatentImage",
+    "_meta": {
+      "title": "EmptySD3LatentImage"
+    }
+  },
+  "16": {
+    "inputs": {
+      "lora_name": [
+        "18",
+        0
+      ],
+      "strength_model": 1,
+      "strength_clip": 1,
+      "model": [
+        "1",
+        0
+      ],
+      "clip": [
+        "4",
+        0
+      ]
+    },
+    "class_type": "LoraLoader",
+    "_meta": {
+      "title": "Load LoRA"
+    }
+  },
+  "17": {
+    "inputs": {},
+    "class_type": "RunningHub_ZImageI2L_Loader",
+    "_meta": {
+      "title": "RunningHub_ZImageI2L_Loader"
+    }
+  },
+  "18": {
+    "inputs": {
+      "seed": 1003065578605367,
+      "pipeline": [
+        "26",
+        0
+      ],
+      "training_images": [
+        "19",
+        0
+      ]
+    },
+    "class_type": "RunningHub_ZImageI2L_LoraGenerator",
+    "_meta": {
+      "title": "RunningHub_ZImageI2L_LoraGenerator"
+    }
+  },
+  "19": {
+    "inputs": {
+      "inputcount": 4,
+      "Update inputs": null,
+      "image_1": [
+        "20",
+        0
+      ],
+      "image_2": [
+        "21",
+        0
+      ],
+      "image_3": [
+        "22",
+        0
+      ],
+      "image_4": [
+        "23",
+        0
+      ]
+    },
+    "class_type": "ImageBatchMulti",
+    "_meta": {
+      "title": "Image Batch Multi"
+    }
+  },
+  "20": {
+    "inputs": {
+      "image": "example_1.jpg"
+    },
+    "class_type": "LoadImage",
+    "_meta": {
+      "title": "Load Image"
+    }
+  },
+  "21": {
+    "inputs": {
+      "image": "example_2.jpg"
+    },
+    "class_type": "LoadImage",
+    "_meta": {
+      "title": "Load Image"
+    }
+  },
+  "22": {
+    "inputs": {
+      "image": "example_3.jpg"
+    },
+    "class_type": "LoadImage",
+    "_meta": {
+      "title": "Load Image"
+    }
+  },
+  "23": {
+    "inputs": {
+      "image": "example_4.jpg"
+    },
+    "class_type": "LoadImage",
+    "_meta": {
+      "title": "Load Image"
+    }
+  },
+  "24": {
+    "inputs": {
+      "preview": "",
+      "source": [
+        "18",
+        1
+      ]
+    },
+    "class_type": "PreviewAny",
+    "_meta": {
+      "title": "Preview as Text"
+    }
+  },
+  "26": {
+    "inputs": {
+      "anything": [
+        "17",
+        0
+      ]
+    },
+    "class_type": "easy cleanGpuUsed",
+    "_meta": {
+      "title": "Clean VRAM Used"
+    }
+  },
+  "28": {
+    "inputs": {
+      "filename_prefix": "zimage_lora",
+      "lora_path": [
+        "18",
+        1
+      ]
+    },
+    "class_type": "RunningHub_ZImageI2L_Saver",
+    "_meta": {
+      "title": "RunningHub_ZImageI2L_Saver"
+    }
+  }
+}