Skip to content
English
Create Support Ticket
  • There are no suggestions because the search field is empty.

Integrating Stability AI with Make.com

Integrating Stability AI with Make.com allows you to automate high-quality image generation—turning a Slack message, a Google Sheet row, or an Airtable record into a professional visual in seconds.

While Make has a "Verified" Stability AI app, you can also use the HTTP module for deeper control over the latest models like Stable Diffusion 3.5 or Ultra. This guide covers both methods.

🔑 Phase 1: Obtain Your Stability AI API Key

Before heading to Make, you need your "fuel" (credits) and your "key" (API access).

  1. Log in to the Stability AI Developer Platform.

  2. Navigate to the API Keys section in the sidebar.

  3. Click + Create Key. Copy it immediately; you won't be able to see it again.

  4. Note: New accounts typically receive 25 free credits. Monitor your balance in the "Billing" tab.

🛠️ Phase 2: Using the Native Make.com App

This is the easiest "no-code" route for standard text-to-image tasks.

1. Add the Stability AI Module

Search for "Stability AI" in the Make scenario editor and select Generate an Image from Text.

2. Establish the Connection

  • Click Add next to the Connection field.

  • Paste your API Key from Phase 1.

  • Give it a name (e.g., "My Stability Account") and save.

3. Configure Parameters

  • Prompt: Map the text from your trigger (e.g., a "New Row" from Google Sheets).

  • Engine: Select the model (e.g., stable-diffusion-xl-1024-v1-0).

  • Style Preset: (Optional) Choose from presets like photographic, digital-art, or neon-punk.

🚀 Phase 3: Advanced Integration (via HTTP Module)

If you want to use the newest v2beta features (like Stable Diffusion 3.5 or Ultra), the native app might not be updated yet. Use the HTTP module instead.

1. Set up the HTTP Request

Add the HTTP > Make a request module and configure it as follows:

  • URL: https://api.stability.ai/v2beta/stable-image/generate/ultra (or your chosen endpoint).

  • Method: POST

  • Headers:

    • authorization: Bearer YOUR_API_KEY

    • accept: image/* (This tells the API to return the actual image file).

  • Body Type: Multipart/form-data

  • Fields:

    • Key: prompt | Value: [Your text prompt]

    • Key: output_format | Value: png

2. Handling the Output

Because the API returns a binary image file, the next module in your scenario (like Google Drive or Airtable) can directly use the Data output from the HTTP module to save the image.

💡 Best Practices & Tips

Error Handling

Stability AI has a strict Safety Filter. If your prompt is flagged, the API will return an error (usually a 403 or a "blur" image).

  • Pro Tip: Add an Error Handler (Ignore or Break) to your Stability module to prevent the entire scenario from stopping if a prompt is rejected.

Aspect Ratios

Instead of just setting width and height, newer models use the aspect_ratio parameter (e.g., 16:9, 1:1, 21:9). Ensure your prompt reflects the style of the ratio you choose.

Cost Management

Every generation costs credits.

  • Stable Image Core: ~3 credits.

  • Stable Diffusion 3.5: ~6.5 credits.

  • Ultra: ~8 credits.

📋 Common Use Cases

Trigger Action Result
Airtable (New Product Name) Stability AI (Text-to-Image) Store product mockup in Airtable
Slack (/generate [prompt]) Stability AI Post the image back to the Slack channel
WooCommerce (New Order) Stability AI Create a unique "Thank You" card image