xai/grok-imagine-image-quality

xAI's Grok Imagine Image Quality, now served by Grok Imagine Image 2.0 at low quality, with output up to 2k

1.2M runs

Readme

Grok Imagine Image Quality

Generate and edit images from text prompts, with output up to 2k resolution.

Now powered by Grok Imagine Image 2.0

xAI retired the original Grok Imagine Image Quality model on November 2, 2026. This model now runs on Grok Imagine Image 2.0 at low quality. That’s the same setting xAI uses for everyone still calling the old model. Your inputs and outputs work the same way as before, and the price went down.

If you want more control, use xai/grok-imagine-image-2 directly. It has a quality input, so you can pick medium when you want finer detail. For the fastest, cheapest generations, use xai/grok-imagine-image.

What you can do with it

Generate images from text

Describe what you want to see and the model creates it. It handles detailed prompts covering subject, style, mood, lighting, composition, and specific real-world entities like brands, locations, and named objects.

Edit existing images

Upload an image and describe how you want it changed. The model applies your edits while keeping the overall structure of the original.

Output at 1k or 2k

Pick 1k (1024px on the long edge) for a faster, cheaper image, or 2k (2048px on the long edge) when you need a high-resolution deliverable. The default is 2k.

Multiple aspect ratios

Choose from square, landscape, portrait, ultrawide, and vertical ratios to match wherever the image is going.

How to write prompts

Be specific. Detailed prompts beat short ones. Describe the subject, the setting, the lighting, the mood, and the style. For example: “A vintage travel poster for Kyoto, Mount Fuji in the background, cherry blossom trees in the foreground, art deco typography, rich color blocks.”

Name real things directly. If you want a specific brand, location, or recognizable subject, name it. The model handles real-world knowledge well.

Add style at the end. Append style directives to steer the look: “oil painting style,” “anime illustration,” “cinematic 35mm film photography,” “pencil sketch on cream paper.”

For editing, describe the change, not the whole image. “Make the sky a dramatic sunset” works better than re-describing every element.

Inputs

  • prompt: text description of the image you want, or instructions for how to edit the input image
  • image (optional): input image for editing. When you provide one, the model edits it based on the prompt instead of generating from scratch. Supports jpg, jpeg, png, webp.
  • aspect_ratio: output aspect ratio (default 1:1). Ignored when editing an image.
  • resolution: 1k or 2k (default 2k)

Pricing

1k output 2k output
Per image $0.04 $0.06
Plus per input image (when editing) $0.01 $0.01

A text-to-image generation at 1k costs $0.04. An edit at 2k (one input image, one output image) costs $0.06 + $0.01 = $0.07.

Try it yourself

Run Grok Imagine Image Quality from the Playground at replicate.com/playground, or call it from your code with the Replicate API.

Model created
Model updated