ERNIE Image · emploidai Marketplace
emploidai Marketplace
Add-onsAppletsPlugins
Search tools, teams, and capabilitiesPublish
MarketplacePluginsERNIE Image
Plugin
Limited listing

ERNIE Image

by langgenius · v0.0.3

Image generation powered by Baidu ERNIE Image models on AI Studio.

212 installsUpdated Jul 21, 2026
Publisher information is incomplete

This community listing does not yet include every recommended support, privacy, pricing, and permission disclosure. Review the available package permissions before installing.

Capabilities

Tools

Available inside your emploidai workspace after installation.

Data sources

Available inside your emploidai workspace after installation.

Category

tool

Version

0.0.3langgenius

Requirements

Maximum memory 256MB

Pricing

Not disclosed by publisher

Security & access

Review before installing

CompatibleRequires emploidai 1.0.0+

Permissions

  • Uses tool capability
  • Requires encrypted tool credentials

Dependencies

No additional dependencies

Resources

Privacy policy
emploidai Marketplace

Discover capabilities. Review access. Install inside your workspace.

DocumentationSecuritySupportPrivacyTerms

ERNIE Image

A Dify tool that generates images with Baidu's ERNIE Image models, served by the AI Studio OpenAI-compatible endpoint.

Localized docs: 简体中文 · 日本語

Samples

Generated with the prompt below, ernie-image-turbo at 1280×720:

Models

ModelNotes
ernie-image-turboFaster, lower latency, suitable for drafts and iteration.
ernie-imageHigher quality, richer detail.

Setup

  1. Sign in at https://aistudio.baidu.com and create an access token from Personal Center → Access Token.
  2. In Dify, install this plugin and authorize it with that token.

Parameters

  • prompt (required) – text description of the image.
  • model – ernie-image-turbo (default) or ernie-image.
  • size – WxH, e.g. 1024x1024, 1024x768, 768x1024, 1280x720, 1792x1024. Default 1024x1024.
  • n – number of images, 1 to 4. Default 1.
  • seed – optional integer for reproducibility.
  • watermark – add a model watermark to the output. Default false.

The tool emits each generated image as a blob and returns the structured response (URLs and revised prompts) as JSON.