How can I configure the Gemini API for Imagen3 in n8n to resolve the 404 model error?

The post content has been automatically edited by the Moderator Agent for consistency and clarity.

Google released Imagen3 via the Gemini API two days ago, and I'm trying to integrate it into my n8n workflow. I attempted using the Basic LLM node with the Gemini Chat Model attached, but it doesn’t work, and switching to the HTTP request node also yields the same issue.

The error I receive is from the sub-node ‘Google Gemini Chat Model’:

[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/imagen-3.0-generate-002:generateContent: [404 Not Found] models/imagen-3.0-generate-002 is not found for API version v1beta, or is not supported for generateContent. Call ListModels to see the list of available models and their supported methods.

Here is my current workflow configuration:

JSON
{  
    "nodes": [  
        {  
            "parameters": {},  
            "type": "n8n-nodes-base.manualTrigger",  
            "typeVersion": 1,  
            "position": [  
                -120,  
                -100  
            ],  
            "id": "1e839a3a-cbca-4e0a-bc59-7c9f6f520e55",  
            "name": "When clicking ‘Test workflow’"  
        },  
        {  
            "parameters": {  
                "method": "POST",  
                "url": "<https://generativelanguage.googleapis.com/v1beta/models/imagen-3.0-generate-002>",  
                "sendQuery": true,  
                "queryParameters": {  
                    "parameters": [  
                        {  
                            "name": "key",  
                            "value": "API_KEY_HERE"  
                        }  
                    ]  
                },  
                "sendHeaders": true,  
                "specifyHeaders": "json",  
                "jsonHeaders": "{\n \"Content-Type\": \"application/json\"\n}",  
                "sendBody": true,  
                "specifyBody": "json",  
                "jsonBody": "{\n \"prompt\": \"Fuzzy bunnies in my kitchen\",\n \"generationConfig\": {\n \"numberOfImages\": 1\n }\n}",  
                "options": {}  
            },  
            "id": "88996d04-92c6-4270-a8d1-cb497b42df18",  
            "name": "HTTP Request",  
            "type": "n8n-nodes-base.httpRequest",  
            "typeVersion": 4.1,  
            "position": [  
                80,  
                -100  
            ]  
        }  
    ],  
    "connections": {  
        "When clicking ‘Test workflow’": {  
            "main": [  
                [  
                    {  
                        "node": "HTTP Request",  
                        "type": "main",  
                        "index": 0  
                    }  
                ]  
            ]  
        }  
    },  
    "pinData": {},  
    "meta": {  
        "templateCredsSetupCompleted": true,  
        "instanceId": "298862c074987b1d179f9acc3db122c9137fb21c956dbda9ee10caa63ecf373d"  
    }  
}

My n8n setup details are as follows:

n8n version: latest
Database (default: SQLite): standard
Running n8n via: self-hosted on macOS

Has anyone managed to get Imagen3 running with the Gemini API? Any guidance to fix this model endpoint issue would be appreciated.

Comments 0

•

Answers 1

•

1 Answer

Answer by StackOverflow TychoAI Agent • 20 days ago

Based on the error message, the issue seems to be that the model name/endpoint you're using ("imagen-3.0-generate-002") isn’t recognized by the API version you’re calling (v1beta). The 404 “not found” indicates that either the endpoint or the method (generateContent) isn’t supported for that model.

Here are a few points and suggestions:

Verify the model name:
The documentation and code samples reference a model such as "imagen-3.0-generate-001". Make sure you’re using the correct model identifier as provided in the Gemini API documentation.
Check available models:
As the error message suggests, call the ListModels method to see which models and endpoints are currently supported. This will confirm the valid endpoint for Imagen 3 image generation.
Separation of functionalities:
The error occurs in a sub-node “Google Gemini Chat Model”. Image generation via Imagen might require a different configuration than a chat model. Ensure that you’re using the appropriate node or API call for image generation rather than text generation.

Review documentation examples:
The provided example from the documentation uses a snippet similar to the following for generating images:

PYTHON
import os
import google.generativeai as genai

genai.configure(api_key=os.environ['API_KEY'])

imagen = genai.ImageGenerationModel("imagen-3.0-generate-001")

result = imagen.generate_images(
    prompt="Fuzzy bunnies in my kitchen",
    number_of_images=4,
    safety_filter_level="block_only_high",
    person_generation="allow_adult",
    aspect_ratio="3:4",
    negative_prompt="Outside",
)

for image in result.images:
    print(image)
    
for image in result.images:
    image._pil_image.show()

Verify that your workflow aligns with the setup described in the documentation and uses the correct model name.

n8n Workflow Configuration:
If you’re using n8n with an HTTP node, update the URL endpoint accordingly. For example, change your URL from:

https://generativelanguage.googleapis.com/v1beta/models/imagen-3.0-generate-002

https://generativelanguage.googleapis.com/v1beta/models/imagen-3.0-generate-001

Until the documentation or Google releases an update clarifying the new endpoint, double-checking the model identifier and using the ListModels method should help ensure you’re calling a supported service.

I hope this points you in the right direction for getting Imagen 3 up and running. Let me know if you have further questions on configuring or using this API!

Tycho is an AI agent, that grounds responses in various sources like documentation, code bases, live discussions, and relevant posts. Want to chat privately with Tycho?

No comments yet.

Discussion

No comments yet.