Try MiniMax FastH3 from Fastvideo →
Models
Agents
Workflows
Studio
PricingBlogDocs
ExploreDiscover models by categoryBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
Generative Media AgentCreate and edit media by chattingWorkflow AgentBuild visual workflows with Agent
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick skills, set tier, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Explore models/
Image GenerationActive

xai / grok-imagine-image-v2

grok-imagine-image-v2

byxai

Create new images or edit a source photo with xAI’s Grok Imagine Image V2. Choose 1K or 2K output, quality level, and aspect ratio.

Text to ImageImage to Image
Model ID
grok-imagine-image-v2
Provider
xai
Updated
1788445099
grok-imagine-image-v2
7
Comments
Average rating : 3.33 (10 users)
Providerxai
Modelgrok-imagine-image-v2
Text to ImageImage to Image
wiro playground—xai/grok-imagine-image-v2
Reset to defaults
0 / 1
Maximum 1 image allowed

Optional. Source image for editing. Max 20MiB. Supported: jpg, jpeg, png. Only 1 image allowed.

Required. Text description of the desired edit.

Sample outputs
Sample 1
Sample 2
Sample 3
Sample 4
Updated 1788445099

## Overview Grok Imagine Image V2 is xAI’s image generation and image editing model. It turns a written instruction into 1–10 images, or edits a single source image while keeping the rest stable. It’s tuned for tight instruction following, cleaner layout control, and sharper on-image text. That makes it useful for real assets like posters, product shots, and social creatives. ## What you can build - Product shots on clean backdrops with controlled lighting and styling - Posters and thumbnails with readable headlines and small print - Social creatives in story, feed, banner, and cinematic formats without manual cropping - Photo restyles like pencil sketch, film still, editorial, or illustration looks - Background swaps and scene changes while preserving the main subject - Iteration loops where you change one detail at a time, not the whole image ## Inputs - A required written instruction that describes the image you want, or the edit you want applied. - An optional source image for editing. It must be a JPG or PNG, up to 20 MiB. This Wiro version accepts only 1 image. - The number of output images you want in one run, from 1 to 10 variations. - A target aspect ratio. You can keep the original framing automatically when editing, or pick a fixed ratio such as 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 2:1, or 5:2. - An output resolution preset: 1K or 2K. - A quality mode: Low for drafts and exploration, Medium for finer detail. ## Outputs - A set of 1–10 generated images. - Each image follows the requested aspect ratio, resolution, and quality mode. - Results come back as image files (typically delivered as downloadable URLs, or as base64-encoded image data depending on the serving system). Common formats include JPEG and PNG. ## Recommended settings - Drafting and exploration: Low quality, 1K resolution, and 4–10 variations. - Final selects: Medium quality, 2K resolution, and 1–2 variations. - Image editing: Keep the aspect ratio set to automatic so the framing stays consistent. ## Limitations - This Wiro model accepts only 1 source image for edits. Some other integrations allow more reference images. - Hosted image links can be temporary. Save the results soon after you generate them. - Dense scenes can drift on small background details, especially at Low quality. - Low-quality inputs reduce edit fidelity. Heavy compression, motion blur, screenshots of screenshots, and scanned images can cause unexpected changes. - Large edits can change parts of the image you did not mention. Ask for smaller, specific changes when you need control. ## Safety & compliance - xAI applies content moderation to generated images. If a request fails moderation, the system may return a filtered placeholder instead of the requested output. - Don’t request sexual content involving minors or any non-consensual intimate imagery. These are blocked. - If your output includes a watermark or provenance signal, don’t remove, alter, or hide it. - You’re responsible for permissions and rights for any photos, logos, and brand assets you upload or reference.

Example prompts

Great starting points for grok-imagine-image-v2.

Make the woman in the image play drums in a studioImage Generation
Change the backpack to blue jean, keep the lighting, shadows and background exactly the sameImage Generation
Place him on a rooftop terrace at golden hour with a city skyline behind, match the lighting on his suit to the warm sunsetImage Generation
Add the headline 'AMALFI' in bold condensed sans-serif across the empty sky at the top, and 'SUMMER 2026' in small letterspaced type beneath itImage Generation

API quick start

Run grok-imagine-image-v2 with a single API call.

POST https://api.wiro.ai/v1/Run/xai/grok-imagine-image-v2
{
  "prompt": "Make the woman in the image play drums in…",
  "samples": 1,
  "resolution": "1k",
  "quality": "low"
}
View full API docs

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingPartnerChangelogStatusFAQ
Getting StartedIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion