MiniMax H3 Image API
Use Text to Image Turbo with model_id set to minimax-h3-image. The API reference lists the current prompt, negative prompt, dimensions, and asynchronous task contract.
Read the Text to Image Turbo APIGet an early look at MiniMax H3 Image, the new AI text-to-image choice in Medux Workshop. Explore unlimited image ideas online: write a scene, choose the canvas size, and generate an original still. Start free with trial credits, see the estimate before submitting, then preview or download the result.
Start with 3,000 free trial credits for eligible tasks. Compare free credits and usage limits.
Describe the subject, scene, composition, lighting, and style.
The latest task appears below. Processing continues on the server if you leave this page.
Content involving minors, non-consensual intimate imagery, or realistic depictions of real people without their consent is not permitted.
No image yet. Generate one to see it here.
Use the service behind this Workshop in your application or AI agent. Explore the API reference and its corresponding MCP tool before starting an integration.
Use Text to Image Turbo with model_id set to minimax-h3-image. The API reference lists the current prompt, negative prompt, dimensions, and asynchronous task contract.
Read the Text to Image Turbo APIThe medux_text_to_image tool exposes this image-generation route to connected AI agents. Select minimax-h3-image explicitly and review the tool arguments before running.
Open the MCP tool documentationWrite a prompt with a subject, setting, and visual direction, or select Use sample to start from the example.
Choose width and height in pixels. Add an optional negative prompt for details to avoid.
Review the credit estimate, generate with MiniMax H3 Image, and download your finished still. You can also return to it in Account Results.
Turn a short character brief into an original portrait with deliberate clothing, lighting, and setting.
Try environments, color palettes, and camera framing for an opening scene or visual pitch.
Download an image and use it as the starting frame in a separate Image to Video workflow.
Name the central subject first, then specify framing, setting, materials, and light.
Compare outputs by changing only the camera angle, palette, or style in your next prompt.
Create original characters or use real-person likenesses only with permission. Review the result before sharing or reusing it.
Every Medux tool has open examples on GitHub: copy a prompt for Claude or Codex, or start from a working API request.
A ready-to-paste prompt and approval checklist for running medux_text_to_image from Claude.
View on GitHubThe same workflow for Codex: expected tool call, arguments to review and how to verify the result.
View on GitHubRequest fields, curl, Python and JavaScript samples, and response handling for this endpoint.
View on GitHubMiniMax H3 Image is a text-to-image model available through Medux Text to Image Turbo. This Workshop selects model_id minimax-h3-image for each task.
Yes. Start online with 3,000 free trial credits as a new Medux user. Explore unlimited AI image ideas with prompts and check the live credit estimate before submitting each eligible image task.
Enter a text prompt, optionally add a negative prompt, set output width and height, then generate. Preview and download the completed image or find it in Account Results.
No. This Workshop creates still images using minimax-h3-image. The separate MiniMax H3 video Workshop creates moving clips.
Yes. Select minimax-h3-image in the Text to Image Turbo API or the corresponding medux_text_to_image MCP tool. Review the current API reference for accepted fields and limits.