8
n8n 한국어amn8n.com

DALL-E 2와 인공지능 검토 루프를 사용하여 생성하고 품질 검사하는 이미지

중급

이것은Content Creation, Multimodal AI분야의자동화 워크플로우로, 11개의 노드를 포함합니다.주로 If, Set, ManualTrigger, SplitInBatches, OpenAi 등의 노드를 사용하며. DALL-E 2와 인공审核 반복으로 이미지 생성 및 품질 검사

사전 요구사항
  • OpenAI API Key
워크플로우 미리보기
노드 연결 관계를 시각적으로 표시하며, 확대/축소 및 이동을 지원합니다
워크플로우 내보내기
다음 JSON 구성을 복사하여 n8n에 가져오면 이 워크플로우를 사용할 수 있습니다
{
  "meta": {
    "instanceId": "ad0113c344ee237399e44e9f11798b05baeb83a6196d514a9ae9d2ad71c3b5c9",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "7b815687-00ea-4dc8-a97c-503ba6e90361",
      "name": "워크플로 시작",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        240,
        4016
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "27c7bcf8-92f6-4e9e-8341-392b41e45728",
      "name": "이미지 프롬프트 설정",
      "type": "n8n-nodes-base.set",
      "position": [
        416,
        4016
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "5f36bc2b-9acb-4159-b9c3-98a6f9650787",
              "name": "Prompt",
              "type": "string",
              "value": "Make an image of an attractive person standing in new york city"
            },
            {
              "id": "e5823995-d822-4f59-b580-c9efaabc465c",
              "name": "Name",
              "type": "string",
              "value": "woman-nyc"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "dca87162-622b-4c42-8642-d60501673a79",
      "name": "참고 사항2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -208,
        3088
      ],
      "parameters": {
        "width": 1600,
        "height": 100,
        "content": "**Need more help?**  \nWebsite: https://ynteractive.com  \nEmail: robert@ynteractive.com"
      },
      "typeVersion": 1
    },
    {
      "id": "899e1ec5-b857-4863-a8d5-a07b8065df8d",
      "name": "항목 루프 처리1",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        496,
        4256
      ],
      "parameters": {
        "options": {
          "reset": false
        }
      },
      "typeVersion": 3
    },
    {
      "id": "27472c1e-6c24-491a-b759-c6d544fbdd6c",
      "name": "참고 사항3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -208,
        3232
      ],
      "parameters": {
        "color": 3,
        "width": 1072,
        "height": 1480,
        "content": "## Step-by-Step Implementation Guide\n\n### Prerequisites\nBefore setting up this workflow, you'll need:\n\n1. **n8n instance** (cloud or self-hosted)\n2. **OpenAI API account** with DALL-E access\n3. **GotoHuman account** for review management\n\n### Step 1: Set Up OpenAI API Credentials\n\n1. Go to [OpenAI's website](https://platform.openai.com/api-keys)\n2. Create an account or sign in\n3. Navigate to \"API Keys\" in your dashboard\n4. Click \"Create new secret key\"\n5. Copy the API key and save it securely\n6. In n8n, go to **Credentials** → **Add Credential** → **OpenAI API**\n7. Paste your API key and save as \"OpenAI account\"\n\n### Step 2: Set Up GotoHuman Credentials\n\n1. Visit [GotoHuman](https://gotohuman.com/) and create an account\n2. Navigate to your API settings/dashboard\n3. Generate an API key\n4. In n8n, go to **Credentials** → **Add Credential** → **GotoHuman API**\n5. Enter your API credentials and save as \"gotoHuman account\"\n\n### Step 3: Configure the Review Template\n\n1. In your GotoHuman dashboard, create a new review template with ID: `3473LaRDbdf03sd6uzYG`\n2. Set up the template with:\n   - **Image field**: For displaying the generated image\n   - **Prompt field**: For showing the original prompt\n   - **Review options**: Approve/Reject buttons\n3. Configure reviewers and notification settings\n\n### Step 4: Import and Configure the Workflow\n\n1. Copy the provided workflow JSON\n2. In n8n, click **Import from File** or **Import from Clipboard**\n3. Paste the workflow JSON\n4. The workflow will automatically create the following nodes:\n\n#### Node Configuration Details:\n\n##### Start Workflow (Manual Trigger)\n- No configuration needed\n- Used to manually start the workflow\n\n##### Set Image Prompt\n- **Prompt**: \"Make an image of an attractive person standing in new york city\"\n- **Name**: \"woman-nyc\"\n- *Customize these values for your specific use case*\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "dd0abc01-e2a4-4892-9b76-547b0573d6c8",
      "name": "초기 검토",
      "type": "@gotohuman/n8n-nodes-gotohuman.gotoHuman",
      "position": [
        704,
        4576
      ],
      "webhookId": "915e31f2-6f70-4e73-af20-2b3423a772c6",
      "parameters": {
        "fields": {
          "value": {
            "Image": "={{\n  JSON.stringify([\n    {\n      url: $json.url,\n      label: 'Generated Image'\n    }\n  ])\n}}\n",
            "Prompt": "={{ $('Set Image Prompt').item.json.Prompt }}"
          },
          "schema": [
            {
              "id": "Image",
              "type": "array",
              "display": true,
              "required": false,
              "displayName": "Image (imageGrid)",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Prompt",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Prompt (text)",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "additionalFields": {},
        "reviewTemplateID": {
          "__rl": true,
          "mode": "list",
          "value": "3473LaRDbdf03sd6uzYG",
          "cachedResultName": "Image Review (3473LaRDbdf03sd6uzYG)"
        }
      },
      "credentials": {
        "gotoHumanApi": {
          "id": "mjB7JPsTP2Uq0ZFX",
          "name": "gotoHuman account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "520b4b3c-0ddc-4349-8af9-66103ace3701",
      "name": "초기 이미지 생성",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        624,
        4384
      ],
      "parameters": {
        "model": "dall-e-2",
        "prompt": "={{ $json.Prompt }}",
        "options": {
          "returnImageUrls": true
        },
        "resource": "image"
      },
      "credentials": {
        "openAiApi": {
          "id": "LC2f70Ar9JzG209n",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "8ef0f626-05d2-4867-be56-b3b2ea045b01",
      "name": "두 번째 이미지 생성",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        1056,
        4464
      ],
      "parameters": {
        "model": "dall-e-2",
        "prompt": "={{ $('Initial Review').item.json.responseValues.Prompt.value }}",
        "options": {
          "returnImageUrls": true
        },
        "resource": "image"
      },
      "credentials": {
        "openAiApi": {
          "id": "LC2f70Ar9JzG209n",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "2761ec7f-7eea-455a-9fdb-edc36028a9d8",
      "name": "두 번째 검토",
      "type": "@gotohuman/n8n-nodes-gotohuman.gotoHuman",
      "position": [
        1248,
        4480
      ],
      "webhookId": "915e31f2-6f70-4e73-af20-2b3423a772c6",
      "parameters": {
        "fields": {
          "value": {
            "Image": "={{\n  JSON.stringify([\n    {\n      url: $json.url,\n      label: 'Generated Image'\n    }\n  ])\n}}\n",
            "Prompt": "={{ $('Set Image Prompt').item.json.Prompt }}"
          },
          "schema": [
            {
              "id": "Image",
              "type": "array",
              "display": true,
              "required": false,
              "displayName": "Image (imageGrid)",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Prompt",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Prompt (text)",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "additionalFields": {},
        "reviewTemplateID": {
          "__rl": true,
          "mode": "list",
          "value": "3473LaRDbdf03sd6uzYG",
          "cachedResultName": "Image Review (3473LaRDbdf03sd6uzYG)"
        }
      },
      "credentials": {
        "gotoHumanApi": {
          "id": "mjB7JPsTP2Uq0ZFX",
          "name": "gotoHuman account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "f2860033-4ce8-4ca2-8a96-b2040ad0ed3d",
      "name": "거부 시",
      "type": "n8n-nodes-base.if",
      "position": [
        928,
        4240
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "159a5db4-20d3-4c84-86bb-a405de6d9ab4",
              "operator": {
                "name": "filter.operator.equals",
                "type": "string",
                "operation": "equals"
              },
              "leftValue": "={{ $json.response }}",
              "rightValue": "rejected"
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "2220b8db-85df-4ec4-a1e5-50d9e20ca25b",
      "name": "참고 사항4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        896,
        3232
      ],
      "parameters": {
        "color": 5,
        "width": 496,
        "height": 1480,
        "content": "##### Loop Over Items1 (Split in Batches)\n- Processes items in batches\n- No additional configuration needed\n\n##### Initial Image Generation (OpenAI)\n- **Resource**: Image\n- **Model**: DALL-E 2\n- **Prompt**: Uses the prompt from \"Set Image Prompt\"\n- **Credentials**: Select your \"OpenAI account\"\n\n##### Initial Review (GotoHuman)\n- **Review Template ID**: 3473LaRDbdf03sd6uzYG\n- **Fields**: Maps image URL and prompt to review form\n- **Credentials**: Select your \"gotoHuman account\"\n\n##### If Rejected (Conditional Logic)\n- Checks if review response equals \"rejected\"\n- Routes to regeneration if rejected\n\n##### Second Image Generation (OpenAI)\n- Same configuration as initial generation\n- Uses updated prompt from review feedback\n\n##### Second Review (GotoHuman)\n- Same configuration as initial review\n- Final quality check\n\n### Step 5: Customize for Your Use Case\n\n1. **Update Image Prompts**: Modify the \"Set Image Prompt\" node with your specific requirements\n2. **Adjust Review Criteria**: Update your GotoHuman template with specific quality guidelines\n3. **Configure Notifications**: Set up email or Slack notifications in GotoHuman for reviewers\n\n### Step 6: Test the Workflow\n\n1. Click **Execute Workflow** on the manual trigger\n2. Monitor the execution flow\n3. Check that images are generated and sent for review\n4. Verify the conditional logic works when images are rejected\n5. Confirm final approved images are properly handled\n"
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "f2860033-4ce8-4ca2-8a96-b2040ad0ed3d": {
      "main": [
        [],
        [
          {
            "node": "8ef0f626-05d2-4867-be56-b3b2ea045b01",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "dd0abc01-e2a4-4892-9b76-547b0573d6c8": {
      "main": [
        [
          {
            "node": "f2860033-4ce8-4ca2-8a96-b2040ad0ed3d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "7b815687-00ea-4dc8-a97c-503ba6e90361": {
      "main": [
        [
          {
            "node": "27c7bcf8-92f6-4e9e-8341-392b41e45728",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "899e1ec5-b857-4863-a8d5-a07b8065df8d": {
      "main": [
        [],
        [
          {
            "node": "520b4b3c-0ddc-4349-8af9-66103ace3701",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "27c7bcf8-92f6-4e9e-8341-392b41e45728": {
      "main": [
        [
          {
            "node": "899e1ec5-b857-4863-a8d5-a07b8065df8d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "8ef0f626-05d2-4867-be56-b3b2ea045b01": {
      "main": [
        [
          {
            "node": "2761ec7f-7eea-455a-9fdb-edc36028a9d8",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "520b4b3c-0ddc-4349-8af9-66103ace3701": {
      "main": [
        [
          {
            "node": "dd0abc01-e2a4-4892-9b76-547b0573d6c8",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
자주 묻는 질문

이 워크플로우를 어떻게 사용하나요?

위의 JSON 구성 코드를 복사하여 n8n 인스턴스에서 새 워크플로우를 생성하고 "JSON에서 가져오기"를 선택한 후, 구성을 붙여넣고 필요에 따라 인증 설정을 수정하세요.

이 워크플로우는 어떤 시나리오에 적합한가요?

중급 - 콘텐츠 제작, 멀티모달 AI

유료인가요?

이 워크플로우는 완전히 무료이며 직접 가져와 사용할 수 있습니다. 다만, 워크플로우에서 사용하는 타사 서비스(예: OpenAI API)는 사용자 직접 비용을 지불해야 할 수 있습니다.

워크플로우 정보
난이도
중급
노드 수11
카테고리2
노드 유형7
난이도 설명

일정 경험을 가진 사용자를 위한 6-15개 노드의 중간 복잡도 워크플로우

저자
Robert Breen

Robert Breen

@rbreen

Professional services consultant with over 10 years of experience solving complex business problems across industries. I specialize in n8n and process automation—designing custom workflows that integrate tools like Google Calendar, Airtable, GPT, and internal systems. Whether you need to automate scheduling, sync data, or streamline operations, I build solutions that save time and drive results.

외부 링크
n8n.io에서 보기

이 워크플로우 공유

카테고리

카테고리: 34