Spiral gives your agent every tool with one account. Browse the tools →

ChatGPT · Image

How to Use Bria Text-to-Image Base in ChatGPT

Bria Text-to-Image Base creates photos and artwork from text, with optional reference guidance for composition. Unlike Bria Text-to-Image Fast, which prioritizes speed, Base suits workflows where you want to refine a visual brief.

Prompts to try with Bria Text-to-Image Base in ChatGPT

Copy an example into ChatGPT, or ask in your own words.

Use Bria Text-to-Image Base to create a square photograph of an unbranded glass perfume bottle on dark stone, with soft side lighting and a restrained amber palette. Exclude lettering and extra bottles.

Bria Text-to-Image BaseChatGPT
Try asking
  • Use Bria Text-to-Image Base to create a wide illustration about rebuilding a habit: a small footbridge being repaired one plank at a time. Use flat colors and leave open space above the bridge.

  • Use Bria Text-to-Image Base to create four portrait artwork concepts of a fictional botanist wearing a green work jacket in a greenhouse. Keep the description unchanged and turn off prompt enhancement.

  • Use Bria Text-to-Image Base with this reference image and depth guidance to explore a reading room with walnut shelves, linen seating, and late afternoon light. Return one image following the reference's proportions.

  • Use Bria Text-to-Image Base to explore the idea of a tiny observatory in a desert. Turn on prompt enhancement and create four wide artwork concepts for comparison.

How to set up Bria Text-to-Image Base in ChatGPT

Pick the way that suits you. Each takes about two minutes.

Use the ChatGPT connector

  1. 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
  2. Click Connect

    ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

  3. 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

  1. Send ChatGPT this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run Bria Text-to-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/bria/text-to-image/base",
        "input": {
          "prompt": "A lone figure stands on the edge of a serene cliff at sunset, gazing out over a vast, mystical valley. The figure is clad in flowing robes that ripple in the…"
        }
      }'

Then paste one of the prompts above: ChatGPT finds Bria Text-to-Image Base on Spiral, shows the price and runs it.

Bria Text-to-Image Base providers and prices

Spiral runs Bria Text-to-Image Base through fal. Open a card for today's price, with every fee included.

falImage
Bria Base · Text to Image
fal-ai/bria/text-to-image/base

Settings you can ask for

Bria Text-to-Image Base works from your prompt. Ask ChatGPT for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Negative promptwhat to leave out, in words

The negative prompt you would like to use to generate images.

Number of images1 to 44

How many images you would like to generate. When using any Guidance Method, Value is set to 1.

Aspect ratio1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16 and 1 more1:1

The aspect ratio of the image. When a guidance method is being used, the aspect ratio is defined by the guidance image and this parameter is ignored.

Seed0 to 2147483647

The same seed and the same prompt given to the same version of the model

will output the same image every time.

Number of inference steps20 to 5030

The number of iterations the model goes through to refine the generated image. This parameter is optional.

Guidance scale (CFG)0 to 205

The CFG (Classifier Free Guidance) scale is a measure of how close you want

the model to stick to your prompt when looking for a related image to show you.

Prompt enhancementon or offoff

When set to true, enhances the provided prompt by generating additional, more descriptive variations, resulting in more diverse and creative output images.

Mediumphotography or art

Which medium should be included in your generated images. Omit or set to null to let Bria select the medium.

Every API field of Bria Base · Text to Image is on its tool page: open its card above.

What can you do with Bria Text-to-Image Base in ChatGPT?

Turn a visual idea into images you can compare and refine in conversation. Describe a subject and intended use, then explore photography, artwork, or a composition guided by a reference image.

Product photo concepts

Explore lighting, surfaces, and backgrounds for a proposed product shoot. Describe an unbranded object and compare several visual directions before choosing the photography brief.

Campaign image exploration

Develop campaign imagery around a specific subject, palette, and setting. Request open space for a headline, then add the actual copy during layout.

Editorial illustrations

Turn an article's central idea into a concrete visual metaphor, such as a seedling growing through pavement for a story about persistence.

Environment concept art

Explore a fictional location's architecture, materials, lighting, and mood before committing to an illustration or production design.

Fictional avatar concepts

Develop portraits of fictional characters for a creative brief. Specify clothing, expression, background, and illustration style.

Reference composition studies

Start with a reference image and use edge or depth guidance to explore a different rendering around its outlines or spatial arrangement.

Color studies from a reference

Use recoloring guidance to explore a new palette around a reference image's geometry. Compare the results before selecting a color direction.

Questions about Bria Text-to-Image Base in ChatGPT

Can ChatGPT use Bria Text-to-Image Base?

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Bria Text-to-Image Base like any built-in tool.

How much does Bria Text-to-Image Base cost in ChatGPT?

$0.052 per generation. Billed on `num_images`, default 4. 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 Bria Text-to-Image Base in ChatGPT?

No. Spiral runs Bria Text-to-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 Bria Text-to-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 Bria Text-to-Image Base runs?

Bria Text-to-Image Base runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.

What is Bria Text-to-Image Base useful for?

Use it to develop product photo concepts, campaign imagery, illustrations, and fictional avatars. Give each image a concrete subject, setting, and visual direction so you have a clear brief to judge the result against.

Can Bria Text-to-Image Base follow an existing composition?

Yes. Edge guidance can follow structural outlines, while depth guidance can influence the scene's spatial arrangement. Treat these as composition controls when exploring a new rendering of a reference.

What changes when I use reference guidance?

Guided generation returns one image and follows the reference image's aspect ratio. If you combine guidance images, they must share the same aspect ratio.

How can I reproduce an image?

Keep the seed, prompt, and model version unchanged. Record those together with your other generation settings before making revisions.

When should I use prompt enhancement or a negative prompt?

Try prompt enhancement when a short brief needs more descriptive detail and you want to explore different interpretations. Use a negative prompt to name unwanted elements, such as lettering or background people.

Get started

Start using Bria Text-to-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 ChatGPT

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options