Text and image workflows
Start from a text prompt. Use image mode to add reference images.
Google's cutting-edge image generation model
OpenAI's GPT-4o image generation model
Flux Kontext standard model with balanced performance
Grok Imagine Image 2.0
When this option is enabled, the output image may be selected by AI Generate and published to the Explore.
The workbench preview is a site sample, not a verified output from this model.
Use Grok Imagine Image 2.0 to turn a written scene into an image or edit a composition with up to five reference images. A fixed per-image price makes it straightforward to compare prompt variations.
Start from a text prompt. Use image mode to add reference images.
Choose Standard; each task creates one image.
Up to 5 images, including uploaded references.
Choose the aspect ratio, resolution and, for video, duration. Review the credit estimate before submitting.
Write a scene description for text-to-image, or choose image mode and add the references you want to edit.
Choose Standard; each task creates one image.
Sign in and submit once. Follow the task in the preview or history, then download the finished result. Processing time depends on the provider queue.
Try product backdrops, character studies or social post visuals. State what must stay unchanged when editing a reference.
A ceramic coffee cup on a pale stone counter, soft morning light from the left, close-up composition, no lettering.Only add references that help define the subject, framing or motion. Remove unrelated files before generating.
Up to 5 images, including uploaded references.
| Resolution | Credits / image |
|---|---|
| Standard | 4 |
Each generated image costs 4 credits.
The final total is rounded up to a whole credit. View plans
Start from a text prompt. Use image mode to add reference images. Up to 5 images, including uploaded references.
Choose Standard; each task creates one image.
Each generated image costs 4 credits. The final total is rounded up to a whole credit.
Your submitted task appears in generation history. You can return to check its status and open completed results.
Text-to-image and edits at 4 credits per image
Back to the generator