This workflow follows the HTTP Request → OpenAI recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "UGC Automation - Model Bake-off (Veo3 Fast vs Kling 3.0)",
"nodes": [
{
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"type": "n8n-nodes-base.telegramTrigger",
"typeVersion": 1.2,
"position": [
0,
600
],
"id": "bo-trigger-0001",
"name": "Telegram Trigger",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"url": "=https://api.telegram.org/bot{{ $env.TELEGRAM_BOT_TOKEN }}/getFile?file_id={{ $('Telegram Trigger').first().json.message.photo.last().file_id }}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
220,
600
],
"id": "bo-getimgpath-0001",
"name": "Get Img Path"
},
{
"parameters": {
"chatId": "={{ $('Telegram Trigger').first().json.message.chat.id }}",
"text": "Got it! Running A/B bake-off: kie veo3_fast vs fal Kling 3.0...",
"additionalFields": {
"appendAttribution": false
}
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
440,
600
],
"id": "bo-progress-0001",
"name": "In Progress",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"resource": "image",
"operation": "analyze",
"modelId": {
"__rl": true,
"value": "gpt-5-mini",
"mode": "list",
"cachedResultName": "gpt-5-mini"
},
"text": "=# Scene Writer -- single-scene UGC video prompt (bake-off tool)\n\nYou will write ONE ~8 second UGC-style video scene prompt for an A/B test. The same prompt and the\nsame reference image will be sent to two different video generators, so the prompt must NOT reference\na model or provider by name.\n\nUGC style rules:\n- Natural, candid, unpolished -- amateur iPhone selfie/video quality, slightly uneven framing, authentic,\n slightly blurry.\n- Character just shows and talks about the product/its benefits based on what's visible in the reference\n image (taste for a drink, design for a bag, features for tech, etc). Do not have them open, eat, or use\n the product -- they are just showing it to camera.\n- Dialogue under 150 characters, casual and conversational, using ... for pauses, no em dashes.\n- Preserve all visible product text/packaging claims accurately; never invent extra claims or numbers.\n\nUser's instructions (caption):\n{{ $('Telegram Trigger').first().json.message.caption }}\n\nReturn ONLY this JSON object, no markdown fences, no commentary:\n{\n \"video_prompt\": \"stringified YAML: dialogue, emotion, voice_type, action, character, setting, camera\",\n \"aspect_ratio_video\": \"9:16 or 16:9, default 9:16\"\n}\n",
"imageUrls": "=https://api.telegram.org/file/bot{{ $env.TELEGRAM_BOT_TOKEN }}/{{ $('Get Img Path').first().json.result.file_path }}",
"simplify": false,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.8,
"position": [
660,
600
],
"id": "bo-scenewriter-0001",
"name": "Scene Writer",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "POST",
"url": "https://api.kie.ai/api/v1/veo/generate",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"contentType": "raw",
"rawContentType": "application/json",
"body": "={\n \"prompt\": \"{{ JSON.parse($('Scene Writer').first().json.choices[0].message.content).video_prompt.replace(/\\n/g, '\\\\n').replace(/\"/g, '\\\\\"') }}\",\n \"model\": \"veo3_fast\",\n \"aspectRatio\": \"{{ JSON.parse($('Scene Writer').first().json.choices[0].message.content).aspect_ratio_video }}\",\n \"imageUrls\": \"https://api.telegram.org/file/bot{{ $env.TELEGRAM_BOT_TOKEN }}/{{ $('Get Img Path').first().json.result.file_path }}\"\n}\n",
"options": {
"batching": {
"batch": {
"batchSize": 1,
"batchInterval": 3000
}
}
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
900,
400
],
"id": "bo-createvideoA-0001",
"name": "Create Video A (kie veo3_fast)",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"amount": 20
},
"type": "n8n-nodes-base.wait",
"typeVersion": 1.1,
"position": [
1120,
400
],
"id": "bo-waitA-0001",
"name": "Wait Video A"
},
{
"parameters": {
"url": "https://api.kie.ai/api/v1/veo/record-info",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "taskId",
"value": "={{ $('Create Video A (kie veo3_fast)').item.json.data.taskId }}"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1340,
400
],
"id": "bo-getvideoA-0001",
"name": "Get Video A",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "bo-vidA-success-1",
"leftValue": "={{ $json.data.successFlag }}",
"rightValue": 1,
"operator": {
"type": "number",
"operation": "equals"
}
},
{
"id": "bo-vidA-success-2",
"leftValue": "={{ $json.data.response.resultUrls[0] }}",
"rightValue": 1,
"operator": {
"type": "string",
"operation": "notEmpty",
"singleValue": true
}
}
],
"combinator": "or"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
1560,
400
],
"id": "bo-ifAsuccess-0001",
"name": "If A Success"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "bo-vidA-failed-1",
"leftValue": "={{ $json.data.successFlag }}",
"rightValue": 2,
"operator": {
"type": "number",
"operation": "equals"
}
},
{
"id": "bo-vidA-failed-2",
"leftValue": "={{ $json.data.successFlag }}",
"rightValue": 3,
"operator": {
"type": "number",
"operation": "equals"
}
}
],
"combinator": "or"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
1780,
300
],
"id": "bo-ifAfailed-0001",
"name": "If A Failed"
},
{
"parameters": {
"chatId": "={{ $('Telegram Trigger').first().json.message.chat.id }}",
"text": "=A (kie veo3_fast) generation failed for task {{ $('Create Video A (kie veo3_fast)').item.json.data.taskId }}. Status code: {{ $json.data.successFlag }}",
"additionalFields": {
"appendAttribution": false
}
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
2000,
200
],
"id": "bo-failAfailed-0001",
"name": "Fail A Failed",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "bo-vidA-attempts-1",
"leftValue": "={{ $runIndex }}",
"rightValue": 30,
"operator": {
"type": "number",
"operation": "lt"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
1780,
500
],
"id": "bo-ifAattempts-0001",
"name": "If A Attempts Left"
},
{
"parameters": {
"chatId": "={{ $('Telegram Trigger').first().json.message.chat.id }}",
"text": "=A (kie veo3_fast) generation timed out for task {{ $('Create Video A (kie veo3_fast)').item.json.data.taskId }}.",
"additionalFields": {
"appendAttribution": false
}
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
2000,
600
],
"id": "bo-failAtimeout-0001",
"name": "Fail A Timeout",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "sendVideo",
"chatId": "={{ $('Telegram Trigger').first().json.message.chat.id }}",
"file": "={{ $json.data.response.resultUrls[0] }}",
"additionalFields": {
"caption": "A: veo3_fast"
}
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
2220,
300
],
"id": "bo-sendvideoA-0001",
"name": "Send Video A",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "POST",
"url": "https://queue.fal.run/fal-ai/kling-video/v3/standard/image-to-video",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"prompt\": \"{{ JSON.parse($('Scene Writer').first().json.choices[0].message.content).video_prompt.replace(/\\\"/g, '\\\\\\\"').replace(/\\n/g, '\\\\n') }}\",\n \"image_url\": \"https://api.telegram.org/file/bot{{ $env.TELEGRAM_BOT_TOKEN }}/{{ $('Get Img Path').first().json.result.file_path }}\"\n}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
900,
800
],
"id": "bo-createvideoB-0001",
"name": "Create Video B (fal kling-3.0)",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"amount": 20
},
"type": "n8n-nodes-base.wait",
"typeVersion": 1.1,
"position": [
1120,
800
],
"id": "bo-waitB-0001",
"name": "Wait Video B"
},
{
"parameters": {
"url": "={{ $('Create Video B (fal kling-3.0)').item.json.response_url }}",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1340,
800
],
"id": "bo-getvideoB-0001",
"name": "Get Video B",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"onError": "continueRegularOutput"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "bo-vidB-ready-1",
"leftValue": "={{ $json.video.url }}",
"rightValue": 1,
"operator": {
"type": "string",
"operation": "notEmpty",
"singleValue": true
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
1560,
800
],
"id": "bo-ifBready-0001",
"name": "If B Ready"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "bo-vidB-attempts-1",
"leftValue": "={{ $runIndex }}",
"rightValue": 30,
"operator": {
"type": "number",
"operation": "lt"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
1780,
900
],
"id": "bo-ifBattempts-0001",
"name": "If B Attempts Left"
},
{
"parameters": {
"chatId": "={{ $('Telegram Trigger').first().json.message.chat.id }}",
"text": "=B (fal kling-3.0) generation failed or timed out. fal request: {{ $('Create Video B (fal kling-3.0)').first().json.response_url }}",
"additionalFields": {
"appendAttribution": false
}
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
2000,
1000
],
"id": "bo-failBtimeout-0001",
"name": "Fail B Timeout",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "sendVideo",
"chatId": "={{ $('Telegram Trigger').first().json.message.chat.id }}",
"file": "={{ $json.video.url }}",
"additionalFields": {
"caption": "B: kling-3.0"
}
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
2220,
800
],
"id": "bo-sendvideoB-0001",
"name": "Send Video B",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Telegram Trigger": {
"main": [
[
{
"node": "Get Img Path",
"type": "main",
"index": 0
}
]
]
},
"Get Img Path": {
"main": [
[
{
"node": "In Progress",
"type": "main",
"index": 0
}
]
]
},
"In Progress": {
"main": [
[
{
"node": "Scene Writer",
"type": "main",
"index": 0
}
]
]
},
"Scene Writer": {
"main": [
[
{
"node": "Create Video A (kie veo3_fast)",
"type": "main",
"index": 0
},
{
"node": "Create Video B (fal kling-3.0)",
"type": "main",
"index": 0
}
]
]
},
"Create Video A (kie veo3_fast)": {
"main": [
[
{
"node": "Wait Video A",
"type": "main",
"index": 0
}
]
]
},
"Wait Video A": {
"main": [
[
{
"node": "Get Video A",
"type": "main",
"index": 0
}
]
]
},
"Get Video A": {
"main": [
[
{
"node": "If A Success",
"type": "main",
"index": 0
}
]
]
},
"If A Success": {
"main": [
[
{
"node": "Send Video A",
"type": "main",
"index": 0
}
],
[
{
"node": "If A Failed",
"type": "main",
"index": 0
}
]
]
},
"If A Failed": {
"main": [
[
{
"node": "Fail A Failed",
"type": "main",
"index": 0
}
],
[
{
"node": "If A Attempts Left",
"type": "main",
"index": 0
}
]
]
},
"If A Attempts Left": {
"main": [
[
{
"node": "Wait Video A",
"type": "main",
"index": 0
}
],
[
{
"node": "Fail A Timeout",
"type": "main",
"index": 0
}
]
]
},
"Create Video B (fal kling-3.0)": {
"main": [
[
{
"node": "Wait Video B",
"type": "main",
"index": 0
}
]
]
},
"Wait Video B": {
"main": [
[
{
"node": "Get Video B",
"type": "main",
"index": 0
}
]
]
},
"Get Video B": {
"main": [
[
{
"node": "If B Ready",
"type": "main",
"index": 0
}
]
]
},
"If B Ready": {
"main": [
[
{
"node": "Send Video B",
"type": "main",
"index": 0
}
],
[
{
"node": "If B Attempts Left",
"type": "main",
"index": 0
}
]
]
},
"If B Attempts Left": {
"main": [
[
{
"node": "Wait Video B",
"type": "main",
"index": 0
}
],
[
{
"node": "Fail B Timeout",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate"
},
"versionId": "00000000-0000-4000-8000-000000000001",
"meta": {
"templateCredsSetupCompleted": true
},
"nodeGroups": [],
"id": "ugcModelBakeoff01",
"tags": []
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
httpHeaderAuthopenAiApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
UGC Automation - Model Bake-off (Veo3 Fast vs Kling 3.0). Uses telegramTrigger, httpRequest, telegram, openAi. Event-driven trigger; 20 nodes.
Source: https://github.com/austinkyle/ugc-ad-automation/blob/main/workflow/builds/model-bakeoff.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Ask questions like “How much did I spend on food last month?” and get instant answers from your financial data — directly in Telegram.
Telegram Trigger, OpenAI, Google Sheets +2
Build a Telegram bot that helps users find AliExpress products using natural language requests. The bot uses OpenAI to optimize search queries, Decodo to scrape product listings, and AI analysis to se
Telegram Trigger, OpenAI, Telegram +3
Voice Note -> Veo 3 AD. Uses telegramTrigger, telegram, openAi, httpRequest. Event-driven trigger; 49 nodes.
Telegram Trigger, Telegram, OpenAI +3
> ⚠️ Disclaimer: This workflow uses Community Nodes and must be run on a self-hosted instance of n8n.
HTTP Request, Telegram Trigger, Telegram +2
Viral Tik Tok Clone Finder. Uses httpRequest, telegramTrigger, openAi, googleSheets. Event-driven trigger; 41 nodes.
HTTP Request, Telegram Trigger, OpenAI +2