Générateur d'images de gâteaux
Ceci est unContent Creation, Multimodal AIworkflow d'automatisation du domainecontenant 11 nœuds.Utilise principalement des nœuds comme Webhook, HttpRequest, Agent, RespondToWebhook, LmChatOpenAi. Générer des images de gâteaux personnalisées avec OpenAI GPT et Replicate Flux Schnell
- •Point de terminaison HTTP Webhook (généré automatiquement par n8n)
- •Peut nécessiter les informations d'identification d'authentification de l'API cible
- •Clé API OpenAI
Nœuds utilisés (11)
Catégorie
{
"id": "DE9G0H2GoX4JpP2C",
"meta": {
"instanceId": "803369b330aff65653c557f3d0dd038a389dc95d5e0aa902bc1df630e482e6a7",
"templateCredsSetupCompleted": true
},
"name": "Cake Image Generator",
"tags": [],
"nodes": [
{
"id": "3bbf3ae1-a1d3-4d8e-8f1a-d620a8cc68fa",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
16,
208
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini",
"cachedResultName": "gpt-4.1-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "ojOuwGjFsedrgBV6",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "65ad017a-d18c-48f9-b315-42d8495204d9",
"name": "Générer une Image",
"type": "n8n-nodes-base.httpRequest",
"position": [
320,
-16
],
"parameters": {
"url": "https://api.replicate.com/v1/models/black-forest-labs/flux-schnell/predictions",
"method": "POST",
"options": {},
"jsonBody": "={\n \"version\": \"latest\",\n \"input\": {\n \"prompt\": \"{{$json['prompt']}}\"\n }\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "1fsT3mjTBKXFask9",
"name": "Replicate API Token"
}
},
"typeVersion": 4.2
},
{
"id": "440001e5-7036-41d9-8a7e-ce14f67a49c1",
"name": "Générateur de Prompt",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-80,
-16
],
"parameters": {
"text": "=You are an expert in creating ai cake images.\nI want you to randomise the cake And put a very specific {{ $json.body.name }} On the cake.\n\nBut remember one thing I don't want you to add anything else other than the prompt In the output. I dont want you to add any quotes Or any other information other than the plain text of the prompt.\n\nAlso wherever you mention to write the name\nInstead of \"{{ $json.body.name }}\" write it \\\"{{ $json.body.name }}\\\"\"\nthe name \\nabin\\ is {{ $json.body.name }}\n\neg : black forest gateau cake spelling out the words \\\"FLUX SCHNELL\\\"\", tasty, food photography, dynamic shot\n\ngive a very detailed prompt so that it can perfectly create the images of the cake",
"options": {},
"promptType": "define"
},
"typeVersion": 2.1
},
{
"id": "23fbd09d-63a5-449a-88f7-fae556de6097",
"name": "L'Utilisateur Envoie une Demande",
"type": "n8n-nodes-base.webhook",
"position": [
-320,
-16
],
"webhookId": "5cfa7429-5637-4c1a-a81c-a53dfb154a5d",
"parameters": {
"path": "5cfa7429-5637-4c1a-a81c-a53dfb154a5d",
"options": {},
"httpMethod": "POST",
"responseMode": "responseNode"
},
"typeVersion": 2
},
{
"id": "e174bbd7-5eeb-41ba-9183-06bd84c42dbc",
"name": "Télécharger l'Image",
"type": "n8n-nodes-base.httpRequest",
"position": [
544,
-16
],
"parameters": {
"url": "={{ $json.output[0] }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "0eff512d-4cfd-492d-b63e-4ab52a49fdb6",
"name": "Répondre aux Demandes",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
768,
-16
],
"parameters": {
"options": {}
},
"typeVersion": 1.4
},
{
"id": "3c788a4d-1e7c-4b49-b9d2-660f93a85826",
"name": "Note Adhésive1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-400,
-80
],
"parameters": {
"color": 4,
"width": 272,
"height": 224,
"content": "Receives user input (e.g., name/occasion) from the Bolt frontend."
},
"typeVersion": 1
},
{
"id": "ca05fccf-4021-4914-b976-1f17dc34346c",
"name": "Note Adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
-96,
-80
],
"parameters": {
"color": 5,
"width": 304,
"height": 416,
"content": "Uses OpenAI GPT to generate a creative cake prompt."
},
"typeVersion": 1
},
{
"id": "44009c51-447b-40dc-a563-bdfa411e93ba",
"name": "Note Adhésive2",
"type": "n8n-nodes-base.stickyNote",
"position": [
224,
-96
],
"parameters": {
"color": 6,
"height": 240,
"content": "Sends the generated prompt to Replicate Flux Schnell to create the cake image."
},
"typeVersion": 1
},
{
"id": "0826cf08-d5fd-4f74-b3a2-06c9cf1f37f5",
"name": "Note Adhésive3",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
-80
],
"parameters": {
"width": 224,
"height": 224,
"content": "Fetches the generated cake image from Replicate."
},
"typeVersion": 1
},
{
"id": "1f9c45e0-8b04-4db7-9a96-5d84b8bd54a7",
"name": "Note Adhésive4",
"type": "n8n-nodes-base.stickyNote",
"position": [
720,
-80
],
"parameters": {
"color": 3,
"height": 224,
"content": "Returns the final cake image URL to the frontend."
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "8ec6e9ea-0764-4692-8dfc-e72156240101",
"connections": {
"e174bbd7-5eeb-41ba-9183-06bd84c42dbc": {
"main": [
[
{
"node": "0eff512d-4cfd-492d-b63e-4ab52a49fdb6",
"type": "main",
"index": 0
}
]
]
},
"65ad017a-d18c-48f9-b315-42d8495204d9": {
"main": [
[
{
"node": "e174bbd7-5eeb-41ba-9183-06bd84c42dbc",
"type": "main",
"index": 0
}
]
]
},
"440001e5-7036-41d9-8a7e-ce14f67a49c1": {
"main": [
[
{
"node": "65ad017a-d18c-48f9-b315-42d8495204d9",
"type": "main",
"index": 0
}
]
]
},
"3bbf3ae1-a1d3-4d8e-8f1a-d620a8cc68fa": {
"ai_languageModel": [
[
{
"node": "440001e5-7036-41d9-8a7e-ce14f67a49c1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"23fbd09d-63a5-449a-88f7-fae556de6097": {
"main": [
[
{
"node": "440001e5-7036-41d9-8a7e-ce14f67a49c1",
"type": "main",
"index": 0
}
]
]
}
}
}Comment utiliser ce workflow ?
Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.
Dans quelles scénarios ce workflow est-il adapté ?
Intermédiaire - Création de contenu, IA Multimodale
Est-ce payant ?
Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.
Workflows recommandés
Nabin Bhandari
@knabinbhandariPartager ce workflow