图像到图像生成
中级
这是一个Content Creation, Multimodal AI领域的自动化工作流，包含 15 个节点。主要使用 Set, Wait, Airtable, HttpRequest, ManualTrigger 等节点。 使用 FLUX.1 Kontext 和 Mistral 通过 AI 增强提示词变换图像
前置要求
- •Airtable API Key
- •可能需要目标 API 的认证凭证
工作流预览
可视化展示节点连接关系，支持缩放和平移
无法加载工作流预览
导出工作流
复制以下 JSON 配置到 n8n 导入，即可使用此工作流
{
"id": "",
"meta": {
"instanceId": "",
"templateCredsSetupCompleted": true
},
"name": "图像到图像生成",
"tags": [],
"nodes": [
{
"id": "",
"name": "当点击\"执行工作流\"时",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-680,
-180
],
"parameters": {},
"typeVersion": 1
},
{
"id": "",
"name": "Airtable",
"type": "n8n-nodes-base.airtable",
"position": [
-380,
-180
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "https://airtable.com/",
"cachedResultName": "YTB Outlier Finder"
},
"table": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "https://airtable.com/",
"cachedResultName": "Image Generation"
},
"options": {
"fields": [
"ImageDescription",
"Situation",
"BaseImage",
"Name"
]
},
"operation": "search",
"filterByFormula": "={Prompt} = \"\""
},
"credentials": {
"airtableTokenApi": {
"id": "",
"name": "Airtable Personal Access Token account"
}
},
"typeVersion": 2.1
},
{
"id": "",
"name": "生成图片",
"type": "n8n-nodes-base.httpRequest",
"position": [
140,
-180
],
"parameters": {
"url": "https://fal.run/fal-ai/flux-pro/kontext/max",
"method": "POST",
"options": {},
"sendBody": true,
"sendHeaders": true,
"bodyParameters": {
"parameters": [
{
"name": "prompt",
"value": "={{ $json.text }}"
},
{
"name": "image_url",
"value": "={{ $('Airtable').item.json.BaseImage[0].url }}"
},
{
"name": "guidance_scale",
"value": "7.5"
},
{
"name": "num_images",
"value": 1
},
{
"name": "safety_tolerance",
"value": 2
},
{
"name": "output_format",
"value": "jpeg"
},
{
"name": "sync_mode",
"value": "false"
},
{
"name": "aspect_ratio",
"value": "1:1"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Key {{ $('Edit Fields').item.json.FalAITOKEN }}"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"retryOnFail": true,
"typeVersion": 4.2
},
{
"id": "",
"name": "记录图像帖子",
"type": "n8n-nodes-base.airtable",
"position": [
640,
-200
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "https://airtable.com/",
"cachedResultName": "YTB Outlier Finder"
},
"table": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "https://airtable.com/",
"cachedResultName": "Table 2"
},
"columns": {
"value": {
"Name": "={{ $('Airtable').item.json.Name }}",
"Prompt": "={{ $json.prompt }}",
"FinalImage": "={{ [{ \"url\": $json.images[0].url}] }}"
},
"schema": [
{
"id": "Name",
"type": "string",
"display": true,
"removed": false,
"readOnly": true,
"required": false,
"displayName": "Name",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "BaseImage",
"type": "array",
"display": true,
"removed": true,
"readOnly": false,
"required": false,
"displayName": "BaseImage",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "ImageDescription",
"type": "string",
"display": true,
"removed": true,
"readOnly": false,
"required": false,
"displayName": "ImageDescription",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Situation",
"type": "string",
"display": true,
"removed": true,
"readOnly": false,
"required": false,
"displayName": "Situation",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Prompt",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Prompt",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "FinalImage",
"type": "array",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "FinalImage",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"Name"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "update"
},
"credentials": {
"airtableTokenApi": {
"id": "",
"name": "Airtable Personal Access Token account"
}
},
"typeVersion": 2.1
},
{
"id": "",
"name": "检查是否已生成",
"type": "n8n-nodes-base.httpRequest",
"onError": "continueErrorOutput",
"position": [
340,
-180
],
"parameters": {
"url": "={{ $json.images[0].url }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "",
"name": "等待",
"type": "n8n-nodes-base.wait",
"position": [
500,
-120
],
"webhookId": "",
"parameters": {
"amount": 3
},
"typeVersion": 1.1
},
{
"id": "",
"name": "Mistral Cloud Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatMistralCloud",
"position": [
-140,
-20
],
"parameters": {
"model": "mistral-large-latest",
"options": {}
},
"credentials": {
"mistralCloudApi": {
"id": "",
"name": "Mistral Cloud account"
}
},
"typeVersion": 1
},
{
"id": "",
"name": "生成提示词",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
-220,
-180
],
"parameters": {
"text": "You are a Image Generation assistant.",
"batching": {},
"messages": {
"messageValues": [
{
"type": "HumanMessagePromptTemplate",
"message": "=You are a creative prompt engineer specializing in generating detailed image-to-image prompts for AI models like Stable Diffusion or Leonardo AI.\n\nYou will receive:\n- A base subject :{{ $json.ImageDescription }}\n- A situation or context that must be represented visually :{{ $json.Situation }}\n\nYour task is to generate an enhanced, imaginative prompt that:\n- Incorporates the visual details from the situation.\n- Respects the base subject’s identity (i.e., the AI will transform an image of the given subject, not create a completely new one).\n- Uses scene-building language to describe environment, mood, lighting, and dynamics.\n- Mentions the style if relevant (e.g., “realistic”, “cinematic”, “fantasy illustration”, etc.).\n- Avoids over-describing the subject's core features (to preserve the base image).\n\nOutput Format:\n- One paragraph of 1–3 sentences.\n- Include keywords or phrases that guide the AI visually (e.g., “dramatic lighting”, “smoke and lava in the background”, “third-person perspective”).\n- Return ONLY the prompt that will be directly given to the Image Generation LLM.\n\nExample Input:\nSubject: “a dog”\nSituation: “the dog is climbing a volcano in eruption”\n\nExample Output Prompt:\n“A dog braving the treacherous slopes of an erupting volcano, surrounded by glowing lava streams and thick clouds of smoke. The sky is darkened with ash as fiery embers illuminate the scene. Realistic style, cinematic lighting, wide-angle perspective.”"
}
]
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
80,
-280
],
"parameters": {
"color": 7,
"width": 760,
"height": 400,
"content": "## 图像生成"
},
"typeVersion": 1
},
{
"id": "",
"name": "便签1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-720,
-280
],
"parameters": {
"color": 7,
"width": 780,
"height": 400,
"content": "## 基础图像和提示词"
},
"typeVersion": 1
},
{
"id": "",
"name": "便签 6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-720,
-700
],
"parameters": {
"color": 7,
"width": 780,
"height": 400,
"content": "## 设置"
},
"typeVersion": 1
},
{
"id": "",
"name": "便利贴5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-720,
-1200
],
"parameters": {
"color": 7,
"width": 500,
"height": 480,
"content": "## 工作原理？"
},
"typeVersion": 1
},
{
"id": "",
"name": "便签2",
"type": "n8n-nodes-base.stickyNote",
"position": [
80,
-920
],
"parameters": {
"color": 7,
"width": 380,
"height": 620,
"content": "## 基础图像"
},
"typeVersion": 1
},
{
"id": "",
"name": "便签3",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
-720
],
"parameters": {
"color": 7,
"width": 360,
"height": 420,
"content": "## 生成的图像"
},
"typeVersion": 1
},
{
"id": "",
"name": "编辑字段",
"type": "n8n-nodes-base.set",
"position": [
-520,
-180
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "",
"name": "FalAITOKEN",
"type": "string",
"value": "[YOUR_API_TOKEN]"
}
]
}
},
"typeVersion": 3.4
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "",
"connections": {
"Wait": {
"main": [
[
{
"node": "Check IF Generated",
"type": "main",
"index": 0
}
]
]
},
"Airtable": {
"main": [
[
{
"node": "Generate Prompt",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields": {
"main": [
[
{
"node": "Airtable",
"type": "main",
"index": 0
}
]
]
},
"Generate Image": {
"main": [
[
{
"node": "Check IF Generated",
"type": "main",
"index": 0
}
],
[]
]
},
"Generate Prompt": {
"main": [
[
{
"node": "Generate Image",
"type": "main",
"index": 0
}
]
]
},
"Check IF Generated": {
"main": [
[
{
"node": "Log Image Posts",
"type": "main",
"index": 0
}
],
[
{
"node": "Wait",
"type": "main",
"index": 0
}
]
]
},
"Mistral Cloud Chat Model": {
"ai_languageModel": [
[
{
"node": "Generate Prompt",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When clicking ‘Execute workflow’": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
}
}
}常见问题
如何使用这个工作流？
复制上方的 JSON 配置代码，在您的 n8n 实例中创建新工作流并选择「从 JSON 导入」，粘贴配置后根据需要修改凭证设置即可。
这个工作流适合什么场景？
中级 - 内容创作, 多模态 AI
需要付费吗？
本工作流完全免费，您可以直接导入使用。但请注意，工作流中使用的第三方服务（如 OpenAI API）可能需要您自行付费。
相关工作流推荐
长转短
将任何YouTube视频转换为病毒式短视频
Set
Code
Wait
+9
17 节点Nasser
内容创作
UGC Nano Banana
使用Nano Banana创建高质量UGC图片（更便宜、更快速）
Set
Split Out
Google Drive
+8
17 节点Nasser
内容创作
实时 - 使用Gemini和Creatomate自动化病毒式AI视频制作与发布
使用Gemini和Creatomate自动化AI视频创作与多平台发布
Set
Code
Wait
+15
47 节点Intuz
内容创作
使用 Gemini AI 和 Airtable 从图片生成 Shopify 产品列表
使用 Gemini AI 和 Airtable 从图片生成 Shopify 产品列表
If
Set
Code
+16
33 节点MANISH KUMAR
内容创作
病毒式标题/缩略图生成
自动化病毒式YouTube标题和缩略图创建（FLUX.1 + Apify）
If
Set
Code
+13
41 节点Nasser
人工智能
YTB 异常值查找器
在您的细分领域中发现隐藏的YouTube趋势/异常视频（Apify + Airtable）
If
Set
Code
+9
16 节点Nasser
