How to Use Z-Image Base in ChatGPT
Z-Image Base turns written briefs into photographs, illustrations, and concept art with control over unwanted content. Choose it when you do not need the custom LoRA support in Z-Image Base LoRA.
Prompts to try with Z-Image Base in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Z-Image Base to create a 1024 × 1024 photograph of a small neighborhood bakery before opening, flour on the counter, warm window light, and no people. Use guidance 4 and 28 steps.
Use Z-Image Base to create a 1536 × 1024 illustration about learning a difficult skill: a beginner repairing a bicycle beside an experienced teacher. Keep the scene focused on their hands and the bicycle, with no lettering.
Use Z-Image Base to explore three fictional botanists with different faces, clothing, and poses in a greenhouse. Make each portrait 1024 × 1024 and show the options separately.
Use Z-Image Base to create a 1536 × 1024 presentation cover showing two teams building a bridge from opposite banks. Leave the upper third uncluttered for my title, and use guidance 4 with 50 steps.
Generate a product photo with Z-Image Base: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first.
How to set up Z-Image Base in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT 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 Z-Image Base
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": "fal-ai/z-image/base", "input": { "prompt": "Grandmother knitting by a window, an empty chair by her" } }'
Then paste one of the prompts above: ChatGPT finds Z-Image Base on Spiral, shows the price and runs it.
Z-Image Base providers and prices
Spiral runs Z-Image Base through fal. Open a card for today's price, with every fee included.
$0.013 per megapixel. image_size presets count as 1 MP; custom sizes round up to whole megapixels. Billed on num_images, default 1.
Settings you can ask for
Z-Image Base works from your prompt. Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Number of inference steps | 1 to 50 | 28 | The number of inference steps to perform. |
| Guidance scale | 1 to 20 | 4 | The guidance scale to use for the image generation. |
| Seed | a whole number | The same seed and the same prompt given to the same version of the model will output the same image every time. | |
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Output format | jpeg, png, or webp | png | The format of the generated image. |
| Acceleration | none, regular, or high | regular | The acceleration level to use. |
| Negative prompt | what to leave out, in words | The negative prompt to use for the image generation. |
Every API field of Z Image Base is on its tool page: open its card above.
What can you do with Z-Image Base in ChatGPT?
Turn an idea discussed in chat into a photograph, illustration, or concept image. Describe the subject, composition, and lighting, then ask for alternatives to choose a visual direction.
Article illustrations
Turn an article's central idea into a photographic scene or stylized illustration. Specify one clear subject and leave space for a headline added during layout.
Product concept images
Explore an imagined product's materials, lighting, and setting before arranging a photo shoot. Describe the object from text and compare several compositions.
Character design exploration
Compare fictional characters with different clothing, poses, and visual treatments. Use the results to choose an art direction.
Environment concept art
Develop settings for a game or story by specifying architecture, weather, viewpoint, and time of day. Compare photographic and illustrated treatments.
Campaign mood boards
Explore a campaign brief through scenes with different compositions, lighting, and artistic styles. Select a direction before producing finished campaign assets.
Website artwork
Generate editorial images for landing pages, onboarding screens, or empty states. Describe the required composition and keep interface text separate.
Presentation cover art
Create a visual metaphor for a presentation, such as a bridge for collaboration or a greenhouse for growth. Reserve an uncluttered area for the slide title.
More on Z-Image Base and ChatGPT
Overview
Z-Image Base in other agents
Questions about Z-Image Base in ChatGPT
Can ChatGPT use Z-Image Base?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Z-Image Base like any built-in tool.
How much does Z-Image Base cost in ChatGPT?
$0.013 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.
Do I need a fal account to use Z-Image Base in ChatGPT?
No. Spiral runs Z-Image Base on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Z-Image Base in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while Z-Image Base runs?
Z-Image Base runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.
What is Z-Image Base good at?
Z-Image Base suits photographic scenes, stylized artwork, and exploring different compositions. Use it when you want several visual directions from a written brief.
What image resolution should I use?
The maker recommends total image areas equivalent to 512 × 512 through 2048 × 2048 pixels, with any aspect ratio. A 1024 × 1024 image is a practical starting point within that range.
Which guidance and step settings should I start with?
Start with guidance 4 and 28 steps, then compare the result with 50 steps. Both sit within the maker's recommended ranges of guidance 3 to 5 and 28 to 50 steps.
How should I use negative prompts?
Describe the scene you want in the main prompt and put unwanted elements in the negative prompt. For a clean product concept, try excluding text, watermarks, and background clutter.
Should I turn guidance up when the image misses my brief?
Try making the subject, placement, and lighting more explicit first. Higher guidance can strengthen prompt adherence, but it can also reduce image quality; start within the recommended 3 to 5 range.
Start using Z-Image Base in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


