Overview

This node performs text-to-image generation using the '海外版 图片生成' resource with the '文生图' operation. It allows users to input a descriptive prompt and generate images based on that text. This is useful for creative projects, marketing materials, or any scenario where visual content needs to be generated from textual descriptions.

Use Case Examples

1. Generating a 3D image of a boy skateboarding in a park based on a text prompt.
2. Creating images with specific aspect ratios and resolutions for social media posts.

Properties

Name	Meaning
提示词	The text prompt describing the image to be generated, e.g., '一个3D形象的小男孩，在公园滑滑板。'
模型	The model used for image generation, with options like jimeng-4.0, Nano-Banana, 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 before continuing.
sessionid	Optional session ID to override the default session ID from credentials.

Output

JSON

• imageUrl - The URL of the generated image.
• prompt - The original text prompt used for image generation.
• model - The model used for generating the image.
• ratio - The aspect ratio of the generated image.
• resolution - The resolution of the generated image.
• isImgReturn - Indicates if the node waited for the image to be returned.

Dependencies

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

Troubleshooting

• If the node throws an error about an unimplemented method, ensure the resource and operation names are correct and supported.
• Errors related to authentication usually indicate missing or invalid API credentials; verify the API key is correctly configured.
• If image generation fails or returns unexpected results, check the prompt format and model selection for compatibility.