AI Models
What each model is good at, where it differs from the others, and what it costs to run.
xAI's current Grok stills model. A Visxy 9:16 library prompt — not the unversioned Imagine row, and not a video model.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Grok Imagine 2.0 is xAI's current stills model. It is not a setting on Grok Imagine. On Visxy it is an image-library prompt you are ready to commit to: 9:16, subject, light, wardrobe.
There is no Grok Imagine 2.0 editor on this catalog row. kie's edit endpoint wants a mask and a task id from a previous kie job. We map neither. Generate a new still, or edit on Grok Imagine.
A finished Grok still from a long library brief. Write the scene, then the light, then the style. 9:16 is on this row. Square and landscape exist when the brief is that shape. There is no auto.
What it is not: the cheap unversioned SKU, a video model, or grok.com's playground. This Visxy row has no quality chip and no size picker. Do not hunt for them.
Against Grok Imagine: 2.0 is the current stills. Imagine is the fast, unversioned try — and the only Grok stills row that can attach a picture. Draft there; finish keepers here with the same prompt.
This is not Grok Imagine Video. A clip is a different page.
Paste the library prompt. Do not "improve" the prose because you changed model. If a Grok Imagine draft already has the pose, reuse the text.
9:16 from the library. One idea.
No Visxy 2.0 still is published yet.
There isn't one here. No public Edit page, no attach-a-reference shape on this row. Generate again, or attach the still to Grok Imagine.
No. Separate catalog row. Imagine is the cheap unversioned stills SKU. This is 2.0.
No. This family has no editor in the Visxy catalog. Edit on Grok Imagine, or generate again.
No. 2.0 is image-only.
