Compare image generation models side-by-side. One API, multiple providers.
Selected models don't support image input. Choose an image-to-image model to upload reference images.
Supported by all 2 selected models
Compression level for lossy formats (JPEG, WebP, AVIF)
// Loading...
Shared params only — uses the first panel's model. Open a panel's icon for that panel's exact request, including any model-specific overrides.
All generations and settings will be cleared.
Add an input image, write a prompt and run
Whether to enable the safety checker.
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
Safety tolerance, 1 is most strict and 5 is most permissive
If `True`, the media will be returned as a data URI and the output data won't be available in the request history.
Background handling. gpt-image-2 does not currently support transparent backgrounds.
Moderation strictness.
Stable end-user identifier used by OpenAI abuse monitoring.
This model requires credits. Please add credits or select a free model.
Each panel will generate that many outputs, multiplying both cost and wait time.
Get $1 in free credits to try any model. Plus unlimited access to free models.
Already have an account? Log in
Schedule a call with the Lumenfall team