How to Use MiniMax H3 Image Text to Image in opencode
MiniMax H3 Image Text to Image creates scenes, illustrations, and visual designs from a written brief. Unlike MiniMax H3 Image Edit, it starts without reference images, making it useful for exploring a new visual direction.
Prompts to try with MiniMax H3 Image Text to Image in opencode
Copy an example into opencode, or ask in your own words.
Read the game's art brief and use MiniMax H3 Image Text to Image to create a 5472 × 3072 cover concept: a lone courier crossing a salt flat toward a radio tower, low morning side light, worn canvas clothing, and open sky in the upper third for a title added later. Include no lettering.
Read the character brief and use MiniMax H3 Image Text to Image for a 4096 × 4096 reference sheet with 2 rows and 3 columns: front, side, and rear views above three expressions. Describe the outfit and proportions consistently in every panel. Include no text.
Use MiniMax H3 Image Text to Image to create a 4096 × 4096 illustrated cover for the project's gardening guide: two hands holding a seedling above dark soil, visible roots, restrained ink linework, and muted green washes. Leave the top quarter empty for typeset copy.
Generate a product photo with MiniMax H3 Image Text to Image: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first. Save the result in ./assets.
Make four logo concepts for a coffee brand called "Northline" with MiniMax H3 Image Text to Image.
How to set up MiniMax H3 Image Text to Image in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run MiniMax H3 Image Text to Image
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "minimax/h3-image/text-to-image", "input": { "prompt": "A rustic farm-to-table feast on a weathered wooden table, overhead food photograph, warm side light" } }'
Then paste one of the prompts above: opencode finds MiniMax H3 Image Text to Image on Spiral, shows the price and runs it.
MiniMax H3 Image Text to Image providers and prices
Spiral runs MiniMax H3 Image Text to Image through fal. Open a card for today's price, with every fee included.
Up to $0.1352 per run at the default inputs. $0.1352 per unit of num_images.
Settings you can ask for
MiniMax H3 Image Text to Image works from your prompt. Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Number of images | 1 to 10 | 1 | The number of images to generate, all from one expanded prompt. |
| Enable prompt expansion | on or off | on | Rewrite the prompt with a language model into a detailed image description before generation. If expansion fails, the request fails instead of generating from the unexpanded prompt. |
| Output format | jpeg, png, webp, or jpg | png | The format of the generated image. |
Every API field of MiniMax H3 Image Text to Image is on its tool page: open its card above.
What can you do with MiniMax H3 Image Text to Image in opencode?
Create artwork and visual design studies alongside the project that needs them. A coding agent can use project briefs and existing assets to specify composition, materials, and exact copy for MiniMax H3 Image.
Game cover and store artwork
Bring a character, setting, and lighting direction together in one image for a game cover or store banner. Specify the subject placement and leave deliberate space for the title.
Character reference sheets
Explore a character's silhouette, clothing, expressions, and proportions in a sheet with explicitly defined rows and columns. Check that the requested details agree across views.
Packaging concepts
Explore a coordinated packaging design for several products. Supply the complete product names and label copy, then define which colors and graphics distinguish each product.
Editorial image concepts
Turn an abstract article theme into a concrete photographic scene. Describe the subject, scale, viewpoint, light, and materials so the visual idea is easy to assess.
Book and card illustrations
Develop cover art or illustrated cards with specified linework, texture, colors, and recurring motifs. State whether lettering belongs in the artwork or will be added later.
Mechanical design studies
Explore vehicle, machine, or product shapes through multiple views and concept diagrams. Define the visible components and treat the result as a design study for review.
More on MiniMax H3 Image Text to Image and opencode
Overview
MiniMax H3 Image Text to Image in other agents
Questions about MiniMax H3 Image Text to Image in opencode
Can opencode use MiniMax H3 Image Text to Image?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run MiniMax H3 Image Text to Image like any built-in tool.
How much does MiniMax H3 Image Text to Image cost in opencode?
Up to $0.1352 per run at the default inputs. $0.1352 per unit of `num_images`. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.
Do I need a fal account to use MiniMax H3 Image Text to Image in opencode?
No. Spiral runs MiniMax H3 Image Text to Image on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up MiniMax H3 Image Text to Image in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while MiniMax H3 Image Text to Image runs?
MiniMax H3 Image Text to Image runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.
What is MiniMax H3 Image good at?
MiniMax H3 Image suits detailed scenes, realistic textures, illustrations, and compositions with specific spatial instructions. MiniMax demonstrates uses including game art, character sheets, packaging, and product diagrams.
What resolution should I use for a detailed final image?
MiniMax recommends about 16 megapixels for best results. Examples include 4096 × 4096 for a square and 5472 × 3072 for a wide landscape.
Can MiniMax H3 Image put readable text in an image?
MiniMax provides guidance for posters, labels, charts, and other images containing text. Quote the exact wording, specify its position and line breaks, and check the rendered copy against your brief.
How should I structure a MiniMax H3 Image prompt?
Start with the intended image and its purpose, then specify the layout, subject positions, and visible details. MiniMax recommends writing the image description in English while keeping any visible lettering in its intended language.
Can MiniMax H3 Image produce a transparent background?
Transparent backgrounds are not supported. MiniMax also lists masked edits and preview images as unsupported.
Start using MiniMax H3 Image Text to Image in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


