xAI · Text to image
Grok Imagine
Grok Imagine Image creates still images from text or transforms a source image using written instructions. Use it to explore photographic, illustrated or stylized scenes, build social-image concepts, and revise an existing visual’s appearance. This family includes Image 1 Standard and Image 2.0 Low in its Quality setting, providing a prompt-led workflow for comparing visual treatments and refining a scene around a recognizable source.
Generation mode
Text to image
Credit cost
4–12 credits
Observed generation time
11 seconds
Release date
Not enough public data
Current credit pricing
| Duration | Configuration | Credits |
|---|---|---|
| 0 seconds | quality | 8 |
| 0 seconds | quality_2k | 12 |
| 0 seconds | standard | 4 |
| 0 seconds | standard_2k | 4 |
Availability and credit rows come from Flowctory's active production catalog. Observed time is shown only after at least five completed generations and is not a controlled benchmark. Model availability, limits, and costs can change.
Use model