Venice AI

Use Venice AI for chat, image generation, embeddings, and more

Actions9

Overview

The node integrates with Venice AI to generate images from text prompts using various configurable parameters. It supports advanced image generation models and options for customizing the output, such as size, style presets, and content filtering. This node is useful in scenarios like creative content creation, marketing material generation, concept art, or any workflow requiring automated image synthesis from textual descriptions.

For example, a user can input a prompt describing a fantasy landscape and receive a generated image matching that description. The node also supports returning the image either as base64-encoded JSON or as raw binary data, enabling flexible downstream processing.

Properties

Name Meaning
Model Image generation model to use (e.g., "hidream").
Prompt Text description of the image to generate.
Additional Fields Collection of optional parameters to customize image generation:
- Negative Prompt Description of elements to exclude from the image.
- Width Width of the generated image in pixels.
- Height Height of the generated image in pixels.
- Steps Number of inference steps controlling generation quality/detail.
- CFG Scale Controls how closely the image follows the prompt (higher = stricter adherence).
- Seed Random seed for reproducibility of results.
- Format Output image format; options are WebP, PNG, JPEG.
- Safe Mode Whether to blur adult content (true/false).
- Hide Watermark Option to hide the Venice watermark on the image (true/false).
- Style Preset Optional style preset to apply (e.g., "3D Model", "Anime").
- Return Binary Whether to return the image as binary data instead of base64 JSON (true/false).

Output

  • The node outputs an object containing a json field with the API response data.
  • If the "Return Binary" option is enabled, the node outputs the image as binary data under the binary.data property, with the filename extension matching the selected format (e.g., .webp, .png, .jpeg).
  • When not returning binary, the output JSON typically contains the generated image data encoded in base64 or URL form depending on the operation variant used.

Dependencies

  • Requires an API key credential for authenticating with the Venice AI service.
  • The node makes HTTP POST requests to Venice AI endpoints for image generation.
  • No additional environment variables are explicitly required beyond the API authentication setup.

Troubleshooting

  • Missing Binary Data Property: For operations like upscaling or editing, if the specified binary image property is not found in the input, the node throws an error indicating the missing property. Ensure the input contains the correct binary data under the expected property name.
  • API Request Failures: Network issues or invalid API credentials may cause request failures. Verify the API key is valid and network connectivity is stable.
  • Invalid Parameter Values: Providing unsupported values for properties like image format or style preset may result in errors or unexpected behavior. Use only supported options.
  • Large Image Sizes or High Steps: Setting very large dimensions or high inference steps may increase processing time or cause timeouts. Adjust parameters accordingly.

Links and References

Discussion