Wanxiang text-to-image

Function introduction

This node encapsulates the Wanxiang text-to-image API. The Wanxiang text-to-image model generates images from a single sentence and is available in V1 and V2. The upgraded text-to-image V2 model enhances semantic understanding and features a built-in intelligent rewriting capability to help you quickly create images. Additionally, V2 supports any resolution, producing images up to 2 million pixels. Prioritize using the text-to-image V2 model. For more information about the API formats, see Text to image and Wanxiang text-to-image V2.

For tips on writing prompts, see Text-to-image Prompt Guide.

Prerequisites

You must have obtained an API key.

Node checklist

Node usage

Example workflow: wanxiang_api_node.json