Actions20
- AI Scrape Actions
- Analyze Sentiment Actions
- Convert to SQL Actions
- Generate Embedding Actions
- HTML to Any Actions
- Image Generation Actions
- Make Prediction Actions
- NSFW Detection Actions
- Object Detection Actions
- Process Image Actions
- Profanity Detection Actions
- Search Web Actions
- Spam Detection Actions
- Speech to Text Actions
- Spell Check Actions
- Summary Actions
- Text to Speech Actions
- Translate Actions
- Translate Image Actions
- Web Suggestion Actions
Overview
This node integrates with the JigsawStack API to generate images based on a text prompt. It is designed for scenarios where users want to create AI-generated visuals from descriptive text, such as generating artwork, concept images, or visual content for marketing and creative projects. The node supports customization of image dimensions, aspect ratio, output format, and generation parameters like denoising steps.
Practical examples include:
- Creating unique illustrations for blog posts or social media.
- Generating product mockups or design concepts from textual descriptions.
- Producing avatars or character designs based on user input prompts.
Properties
| Name | Meaning |
|---|---|
| Prompt | The text prompt describing what the image should depict; this is required to generate the image. |
| Return Type | Format in which the generated image is returned: Base64 encoded string, URL link, or binary data. |
| Aspect Ratio | The width-to-height ratio of the generated image. Options include 1:1, 16:9, 2:3, 21:9, 3:2, etc. |
| Width | Width of the generated image in pixels (range: 256 to 1920). |
| Height | Height of the generated image in pixels (range: 256 to 1920). |
| Steps | Number of denoising steps during image generation (range: 1 to 90), affecting quality and detail. |
| Output Format | File format of the generated image: PNG or SVG. |
| URL | A valid URL where the generated image will be sent (optional, for direct upload or webhook usage). |
| File Store Key | Key used to store the generated image in file storage (optional). |
| Advance Config | Advanced configuration options provided as JSON for fine-tuning the image generation process. |
Output
The node outputs the generated image data in the format specified by the "Return Type" property:
- URL: A JSON field containing a URL pointing to the generated image.
- Base64: A JSON field containing the image encoded as a Base64 string.
- Binary: The image data is output as binary, suitable for further processing or saving as a file within n8n.
The exact structure includes a json object with the relevant image data depending on the chosen return type. If binary is selected, the image is available in the binary data output.
Dependencies
- Requires an active API key credential for the JigsawStack API.
- Network access to
https://api.jigsawstack.com/v1. - Proper configuration of the API key in n8n credentials to authenticate requests.
Troubleshooting
- Invalid API Key or Authentication Errors: Ensure the API key credential is correctly set up and has necessary permissions.
- Invalid Prompt or Parameters: The prompt must be a non-empty string; width, height, and steps must be within allowed ranges. Check that aspect ratio and output format are valid options.
- Network Issues: Verify internet connectivity and that the API endpoint is reachable.
- Unsupported Return Type Handling: If binary output is selected, ensure downstream nodes can handle binary data properly.
- Error Responses from API: Inspect error messages returned by the API for hints on misconfiguration or quota limits.
Links and References
- JigsawStack API Documentation (for detailed API capabilities and parameter explanations)
- n8n Documentation (for general guidance on using custom nodes and handling binary data)