ComfyUI Image Transformer
AI-generatedOverview
This node integrates with ComfyUI to transform and enhance images using customizable workflows defined in JSON format. It supports image-to-image transformations such as img2img, inpainting, and style transfer by uploading an input image, running it through a specified ComfyUI workflow, and returning the processed image.
Common scenarios include:
- Enhancing or modifying images based on AI-driven workflows.
- Applying artistic styles or effects to existing images.
- Automating image editing tasks within an n8n workflow.
Practical example:
- You provide a base64-encoded photo and a ComfyUI workflow that applies a style transfer effect. The node uploads the image, runs the workflow, and outputs the stylized image for further use or storage.
Properties
| Name | Meaning |
|---|---|
| Workflow JSON | The ComfyUI workflow definition in JSON format describing the image processing pipeline. |
| Input Type | Specifies how the input image is provided: URL, Base64 string, or Binary data from input. |
| Input Image | The URL or base64-encoded string of the input image (required if Input Type is URL or Base64). |
| Binary Property | The name of the binary property containing the image data (required if Input Type is Binary). |
| Image Node ID | The node ID within the ComfyUI workflow that loads the input image (usually a LoadImage node). |
| Timeout | Maximum time in minutes to wait for the image generation process before timing out. |
Output
The node outputs an array of items, each containing:
jsonobject with:mimeType: MIME type of the output image (e.g.,image/png,image/jpeg).fileName: Filename of the generated image.data: Base64-encoded string of the image data.status: Status information returned from ComfyUI about the generation process.
binaryobject with:data: The image file encoded in base64 along with metadata:fileName: Filename of the image.fileType: Always"image".fileSize: Approximate size in kilobytes.fileExtension: File extension (e.g.,png,jpg).mimeType: MIME type of the image.
This structure allows easy downstream usage of the generated image either as binary data or JSON metadata.
Dependencies
- Requires access to a ComfyUI API endpoint with a valid API URL and an API key credential for authentication.
- The node uses HTTP requests to communicate with the ComfyUI server, including endpoints for system stats, image upload, prompt submission, and result retrieval.
- Requires n8n helper functions for HTTP requests and binary data handling.
Troubleshooting
- Invalid workflow JSON: If the workflow JSON is malformed or not a valid object, the node throws an error. Ensure the JSON syntax is correct and the workflow structure matches ComfyUI expectations.
- LoadImage node not found: The specified Image Node ID must exist in the workflow and be of the correct type. Verify the node ID matches a LoadImage node.
- Binary property missing or invalid: When using binary input, the specified binary property must exist and contain image data. If not found, the node attempts to find an alternative image property; otherwise, it errors out.
- Unsupported media type: Only image MIME types are supported for input. Non-image binary data will cause an error.
- Timeouts: If image generation takes longer than the configured timeout (default 30 minutes), the node throws a timeout error.
- API connection issues: Failure to connect or authenticate with the ComfyUI API results in errors. Check API URL, credentials, and network connectivity.
- No image outputs found: If the workflow completes but no output images are returned, the node errors out. Confirm the workflow produces image outputs.
Links and References
- ComfyUI GitHub Repository – Official source and documentation for ComfyUI.
- n8n Documentation – General guidance on creating and using custom nodes in n8n.
- FormData npm package – Used internally for multipart form uploads.