Overview

This node generates images from text prompts using various AI models. It is useful for creating visual content based on descriptive text, such as generating a 3D image of a boy skateboarding in a park. Users can specify the model, aspect ratio, resolution, and whether to wait for the image to be returned synchronously.

Use Case Examples

1. Generating a 3D style image of a small boy skateboarding in a park by providing a descriptive prompt.
2. Creating images with different aspect ratios and resolutions for use in design or creative projects.

Properties

Name	Meaning
提示词	The text prompt describing the image to be generated.
模型	The AI model used for image generation, with options like jimeng-4.0, jimeng-3.1, etc.
宽高比	The aspect ratio of the generated image, such as 1:1, 16:9, 21:9, etc.
分辨率	The resolution of the generated image, either 1k or 2k.
是否等待图片返回	Boolean flag indicating whether to wait for the image to be returned synchronously.
sessionid	Optional session ID to override the default credential session ID.

Output

JSON

• imageUrl - The URL or data of the generated image returned from the AI model.

Dependencies

• An API key credential for authentication with the image generation service.

Troubleshooting

• Errors may occur if the prompt is empty or invalid; ensure the prompt is descriptive and non-empty.
• If the selected model is not supported or unavailable, the node will throw an error; select a valid model from the options.
• Network or authentication errors may occur if the API key credential is missing or invalid; verify credentials are correctly configured.