Image generation on elvex is only available to customers who have configured an image generation provider. Users must use an agent to generate images and are blocked from doing so on the Home App.
Step 1: Set up an Image Generation Provider
Before using image generation in any agent, an Owner or Admin must configure an image generation model:
Go to Settings > Apps
Under Image generation provider, select a provider from the dropdown
Press the Save button
Note: elvex supports multiple image generation providers, including OpenAI and Google AI.
Step 2: Enable Image Generation for an Agent
By default, agents don't have image generation enabled. To enable it:
Go to your agent settings screen
Expand the Actions section
Enable the Image Generation action
Step 3: Generate Your First Image
Once enabled, you can generate images by asking your agent and providing a description:
Open a conversation with your agent
Type a request like: "Create an image of a dog chasing a cat in a sunny, summer mountain landscape"
The system will use the latest available model for your configured provider. For OpenAI, the default is GPT Image 1.5, and for Google, the default is Gemini 3.1 Flash Image Preview (aka Nano Banana 2).
Note for OpenAI users: If you encounter an error when using GPT Image 1.5, your administrator may need to verify your OpenAI account. Please go to: https://platform.openai.com/settings/organization/general and click on Verify Organization. Note that it may take up to 15 minutes for the changes to propagate.
Crafting Effective Prompts
To get the best results from image generation:
Be specific in your descriptions
Include details about style, lighting, and composition
Use adjectives to convey mood and atmosphere
Example: "Generate an image of a futuristic cityscape at sunset, with flying cars and neon signs, in a cyberpunk style"
Iterate on Generated Images
If the first result isn't quite what you wanted:
Analyze what aspects of the image you'd like to change
Modify your prompt to address these aspects
Try generating the image with a different model
Generate a new image with the updated prompt
Use Advanced Features
For OpenAI's GPT Image 1.5, you can create images with transparent backgrounds by specifying it in your prompt
Experiment with different image sizes (OpenAI only) and styles
Google AI models offer fast generation with competitive quality
Image Generation Parameters
elvex supports multiple image generation providers and models, each with its own capabilities. If you want to change a parameter for an agent, just use natural language to describe the parameter. For example: "Generate a landscape image of a highway interchange" or "Create an image of a cat with a transparent background"
Providers & Models
OpenAI
GPT Image 1.5 (default)
Latest image model from OpenAI, introduced in December 2025
Supports conversational editing to previously generated photos
size: Options include "1024x1024" (default), "1536x1024" (landscape), "1024x1536" (portrait), or "auto"
background: Options are "transparent", "opaque", or "auto" (default)
GPT Image 1
Released April 2025
Same general capabilities as GPT Image 1.5, but less advanced. Serves as a good backup if GPT Image 1.5 malfunctions or is temporarily unavailable
Note: When using "auto" for size, it defaults to "1024x1024".
Google AI
Gemini 3.1 Flash Image Preview (Nano Banana 2)
Latest image model from Google, introduced in February 2026
High efficiency counterpart to Gemini 3 Pro
Advanced image generation capabilities with faster speeds
Gemini 3 Pro Image Preview (Nano Banana Pro)
Introduced November 2025
Advanced image generation capabilities
Gemini 2.5 Flash Image
Released June 2025
Fast generation with competitive quality
Troubleshooting
Common Issues and Solutions
OpenAI Error: "Need to verify your organization settings"
Solution: Go to https://platform.openai.com/settings/organization/general and click on Verify Organization. Note that it may take up to 15 minutes for the changes to propagate