Overview
This node integrates with Venice.ai to generate and manipulate images using AI models. It supports two main operations:
- Generate: Create new images from textual descriptions (prompts). This is useful for creative content generation, concept art, marketing visuals, or any scenario where you want to produce unique images based on descriptive input.
- Upscale: Enhance the resolution and quality of existing images, making them sharper and more detailed. This is beneficial for improving low-resolution images or preparing images for print or high-quality display.
Practical examples include generating a fantasy landscape from a prompt like "a serene mountain lake at sunset" or upscaling a small logo image to a higher resolution without losing quality.
Properties
| Name | Meaning |
|---|---|
| Model | The AI model used for image generation. Default is "venice-sd35". |
| Prompt | A text description of what you want the AI to generate as an image. |
| Generation Options | Collection of options customizing image generation: - Width: Width of the generated image (64–1280 px) - Height: Height of the generated image (64–1280 px) - CFG Scale: How strictly the image follows the prompt (0.1–20) - Format: Image format to return (JPEG, PNG, WebP) - Hide Watermark: Whether to hide the Venice watermark (may not always be honored) - Negative Prompt: Features to exclude from the image - Return Binary: Return binary image data instead of base64 - Safe Mode: Blur images classified as adult content - Seed: Random seed for generation (0 for random) - Steps: Number of diffusion steps (1–30; higher means more detail but slower) - Style Preset: Apply a predefined style (e.g., "3D Model", "Analog Film", "Anime") |
| Image | Base64-encoded image or URL to upscale (used only in Upscale operation). |
| Scale | Scale factor for upscaling the image (1–4). |
| Upscale Options | Collection of options for upscaling: - Enhance: Whether to enhance the image during upscaling - Enhance Creativity: Creativity level when enhancing (0–1) - Enhance Prompt: Style to apply during enhancement (e.g., "gold", "marble") - Replication: Strength of preserving lines and noise in the base image (0–1) |
Output
For Generate operation:
- If
Return Binaryis false (default), output JSON containing the API response with generated image data encoded (likely base64). - If
Return Binaryis true, outputs binary image data with metadata including:fileName: Generated filename with timestamp and extensionfileExtension: Image file extension (jpg, png, webp)contentType: MIME type of the imagesize: Size of the image data in bytes
- The binary data can be used directly in workflows requiring image files.
- If
For Upscale operation:
- Always returns binary image data with similar metadata fields as above, representing the upscaled image.
Dependencies
- Requires an API key credential for authenticating with the Venice.ai API.
- The node makes HTTP POST requests to
https://api.venice.ai/api/v1/image/generatefor generation and/image/upscalefor upscaling. - Proper configuration of the API key credential in n8n is necessary.
Troubleshooting
Common issues:
- Invalid or missing API key will cause authentication errors.
- Providing invalid parameter values (e.g., width/height out of range) may result in API errors.
- Large image sizes or high step counts may increase processing time or cause timeouts.
- Setting
Hide Watermarkmay not always remove watermarks depending on content. - Returning binary data requires proper handling downstream to avoid data corruption.
Error messages:
- Authentication failures: Check that the API key credential is correctly set.
- Parameter validation errors: Verify all input properties meet specified constraints.
- Network or timeout errors: Ensure stable internet connection and reasonable parameter values.
Links and References
- Venice.ai Official Website — For more information about the service and available models.
- Image Generation Concepts — Background on AI-based image generation.
- Diffusion Models — Technical details on the underlying technology used for image generation.