Skip to main content

xAI's Grok Imagine Image 2.0 edits one to five reference images from a written instruction; name them Image 1, Image 2 and so on to give each its own role, then choose one of five aspect ratios.

From $0.028/image

Workbench

Input

Image editing
170/8000

Reordering updates prompt references. Removing media also removes its references; review your prompt.

Use up to 8,000 characters to request changes, naming sources Image 1, Image 2 and onward; prompt length does not change the fixed image rate. at least 1 characters · at most 8000 characters
1/5

Drop files or media links, paste, or browse · Up to 5 files · Max 10 MB · JPG · PNG · WEBP · GIF

  • Image 1
1 / 5 files
Provide 1–5 source image URLs for the edit; input count is not a separate price tier. at least 1 items · at most 5 items
Editing supports 1:1, 2:3, 3:2, 16:9 and 9:16; the default is 1:1 and every shape uses the same charge.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
lipstick-on-the-collarExample result

Missing the model you need?

SMALL SCENES AND FOCUSED IMAGE CHANGES

Grok Imagine Image 2.0 API at a glance

Draw a mossy robot gardener from words, or give an existing tea tin a new painted label.

Image workflows
2
Create from a description or edit supplied pictures.
Sources for an edit
5
Reference each input as Image 1, Image 2 and onward.
Prompt character limit
8,000
Describe the picture or the changes within this limit.
Square to landscape
5 RATIOS
Available shapes are 1:1, 2:3, 3:2, 16:9 and 9:16.
Shape-independent price
1 rate
Changing aspect ratio does not change the image price.

Results

What you can make with Grok Imagine Image 2.0

  • A shirtless man in tailored trousers holds a silk shirt in a warmly lit fitting room, repeated consistently in angled mirrors.

    Mirrored portrait composition

    One fitting room, repeated reflections

    The 2:3 fitting-room example shows a man holding a silk shirt amid angled mirrors and warm boutique light. His reflection repeats consistently across the mirrors in this result. Use the scene as a reference for directing the subject, wardrobe prop, room, and lighting together; check each reflection in your own result rather than assuming the same outcome for every arrangement.

    Generated example at 2:3: the angled mirrors repeat the man's reflection consistently.

  • A moss-covered little robot waters a bonsai on an old wooden shelf, with blurred potted herbs behind.

    Text-made miniature

    A mossy gardener at bonsai scale

    Our robot-gardener test rendered a moss-covered character watering a bonsai with convincing macro texture. A small subject, a clear action, and a close photographic view give the scene a readable scale. Describe the surface and lighting you want, then assess those details in the returned picture; this test supports the pictured miniature rather than a general score for image quality.

    Macro-style gardener sample generated from a text description.

  • A turquoise tea tin carries a pink-and-white plum-blossom label with gold leaf.

    Directed packaging edit

    Replace the label and preserve its setting

    In the tea-tin test, a hand-painted plum-blossom label with gold leaf replaced the plain design while the lid, table, and light were retained. That result shows a focused edit with named preservation goals. Reference the tin as Image 1, explain the new label, and list the surrounding details that should stay, then compare the edit with the source photograph.

    Label-edit sample retaining the original lid, table and illumination.

Content test

Is Grok Imagine Image 2.0 uncensored? What we tested

Content levels tested on Grok Imagine Image 2.0, by mode
LevelText to imageImage editing
Mild
RefusedTested Nov 11, 2026
Not tested yet
Moderate
RefusedTested Nov 11, 2026
RefusedTested Nov 11, 2026
Strong
RefusedTested Nov 11, 2026
RefusedTested Nov 11, 2026
Very strong
RefusedTested Nov 11, 2026
Not tested yet
Maximum
RefusedTested Nov 11, 2026
Not tested yet
How we test

How each mode behaves

All modes
Generated image files remain available for 14 days before deletion.
All modes
Prompts are capped at 8,000 characters for Grok Imagine Image 2.0.
Image editing
An edit requires between one and five source images.

Use cases

What to build with the Grok Imagine Image 2.0 API

  • Boutique fashion scene concepts

    Plan a portrait around clothing, warm shop lighting, and angled mirrors. The fitting-room sample uses 2:3 and shows the same man repeated consistently in the reflections, giving a concrete reference for this composition.

  • Miniature worlds with material detail

    Describe a small character doing a recognizable job rather than listing objects without a relationship. Our moss-covered robot watered a bonsai, and the test showed the textured surface treatment of a macro scene.

  • Packaging artwork on an existing tin

    Keep an accepted product photograph as the starting point and request a new label. The measured tea-tin edit added hand-painted plum blossoms and gold leaf while retaining the lid, tabletop, and lighting.

  • Edits with assigned reference roles

    Use up to five input pictures when a brief needs more than one source. Explain what each numbered image contributes and identify the details to retain; the available input count is a control, not evidence that every composition will match a reference.

  • Portrait and landscape concept layouts

    Choose a tall, square, or wide canvas before generating a scene for its intended placement. Five ratios are available to generation and editing, and moving between those shapes leaves the image rate unchanged.

Prompts

Grok Imagine Image 2.0 prompt examples you can copy

  • Text to image

    Silk shirt among angled mirrors

    A shirtless man in tailored trousers in a mirrored fitting room holding a silk shirt against his chest, his reflection repeated in the angled mirrors, warm boutique light, confident half smile, photorealistic.

    Why it works. The scene connects a wardrobe prop to a mirrored setting and a restrained expression. Select 2:3 separately; the displayed fitting-room result shows consistent reflections in that particular arrangement.

    Try this prompt
  • Text to image

    A small gardener at work

    A tiny moss-covered robot gardener watering bonsai trees on a sunny balcony shelf, macro photo, shallow depth of field.

    Why it works. Material, scale, and action work together here. The supplied gardener test supports the macro texture direction; this rephrased prompt is a suggestion for another run.

    Try this prompt
  • Text to image

    Amber lounge conversation

    A woman in her forties in a dark green satin evening dress and a man in his forties in an open-collar linen shirt sit close at a quiet hotel lounge table. They share an amused glance, amber lamps reflect in the window, and the city outside is softly blurred. Candid photographic mood.

    Why it works. A clear adult cast, clothing, setting, and shared gesture define the mood without an overloaded scene. This is a proposed prompt rather than a measured sample.

    Try this prompt
  • Image editing

    A painted label for the tea tin

    Wrap the tin from Image 1 in a hand-painted label with plum blossoms and gold leaf, keep the lid, the table and the light.

    Why it works. The instruction names a replacement and a preservation list. Our tea-tin result retained those surrounding details; inspect them again in any new edit.

    Try this prompt
  • Image editing

    A portrait with an evening wardrobe

    For the authorized portrait of a woman in her forties in Image 1, change her outfit to a navy evening dress with bare shoulders. Keep her expression, the doorway behind her, and its warm lamp light. Preserve her identity without imitating another person.

    Why it works. Use a photo you have the right to edit, with an adult subject and no impersonation. This proposed clothing revision separates the change from the expression and setting to retain; it has no measured result on this page.

    Try this prompt
  • Image editing

    Assign a role to each product source

    Use Image 1 as the tea-tin photograph and Image 2 as the source for the painted botanical label design. Apply that artwork to the tin while preserving the lid, table position, and lighting from Image 1.

    Why it works. Numbered roles clarify what two references contribute. This is a suggested multi-source brief, separate from the measured single-tin label edit.

    Try this prompt

Pricing

Grok Imagine Image 2.0 API pricing

One image starts at $0.028.

Get started

How to use the Grok Imagine Image 2.0 API in three steps

  1. Step 1

    Choose generation or editing

    Begin with a written scene for a new picture, or bring one to five source images for a revision. Use photos you have the right to use; any people in edit inputs must be adults, with no impersonation.

  2. Step 2

    Describe the scene or change

    Give a new scene its subject, action, setting, and light. For an edit, assign roles to Image 1, Image 2, and later inputs, then name the details to preserve.

  3. Step 3

    Set a shape for the placement

    Pick 1:1, 2:3, 3:2, 16:9, or 9:16 according to the intended composition. The default is square, and the ratio does not alter the per-image rate.

Parameter reference and code samples are in the API and Readme tabs at the top of this page.

FAQ

Grok Imagine Image 2.0 API FAQ

About Grok Imagine Image 2.0

Start Grok Imagine Image 2.0 with a scene you can describe or a source picture you want to revise. The fitting-room example gives a portrait composition to inspect, the moss gardener shows a miniature texture study, and the tea tin demonstrates an edit with surrounding details retained. Choose the canvas ratio before submitting, assign roles to any reference images, and check the current per-image rate here. Review the result against your brief, keeping preservation goals separate from changes. Save accepted images during the 14-day availability window so the next revision starts from a file you hold.

All Grok models8

Image models1

  • Grok Imagine Image 2.0CurrentText to image · Image editing$0.028per image

Text models4

Related models and next tasks