skills.rest
iptag
iptagCOMMUNITY
Explore all skills by this author →
GitHub

jimeng-api

Generate text-to-image and image-to-image outputs via the Jimeng API.

1.0k|304|Updated Sep 28, 2025
Search Tags:#image generation#visual content#AI art#Jimeng#text-to-image#Dreamina#image-to-image
One-click install
npx skills add https://github.com/iptag/jimeng-api --skill jimeng-api
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jimeng-api
Source: https://github.com/iptag/jimeng-api/tree/main/jimeng-api
Command: npx skills add https://github.com/iptag/jimeng-api --skill jimeng-api

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, Pillow, and includes scripts (resource) components.

What problem does it solve?

This Skill eliminates the manual effort and complexity of generating AI images and art, allowing you to quickly create visual content without needing deep technical expertise or direct interaction with complex APIs. It streamlines the process of turning ideas into visuals, saving you time and creative energy.

Core Features & Use Cases

  • Text-to-Image Generation: Transform simple text prompts into stunning visual artwork, illustrations, or realistic images.
  • Image-to-Image Composition: Modify existing images, apply new styles, or blend multiple visuals based on textual guidance.
  • Customizable Outputs: Easily control aspect ratios (e.g., 16:9, 1:1), resolutions (1k, 2k, 4k), and AI models to match your exact creative vision.
  • Automated Local Saving: All generated images are automatically downloaded, converted to PNG, and saved to your project's /pic directory for immediate use.
  • Use Case: Imagine you need marketing visuals for a new product. Use this Skill to quickly generate multiple image variations from a text description or transform existing product photos into new styles, saving design time and effort.

Quick Start

Generate a 2K 16:9 image of a futuristic city at sunset using Jimeng.

Frequently Asked Questions about jimeng-api

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text prompts using AI?▼

Text-to-image generation converts your written descriptions into visual artwork. This Skill uses the Jimeng API to transform prompts into images with customizable aspect ratios and resolutions, automatically saving outputs as PNG files to your project directory.

Can I modify existing images with AI-guided style changes?▼

Yes, image-to-image generation lets you transform existing images by applying new styles or blending visuals based on text guidance. This Skill supports style transfer and modification through the Jimeng API with configurable sample strength and negative prompts.

What setup do I need before generating images with this Skill?▼

You need a local Jimeng API endpoint running, a valid session-id for authentication, and the requests and Pillow libraries installed. The Skill requires these prerequisites to connect and process image generation requests.

How do I control image quality, size, and style in generated outputs?▼

Configure aspect ratios (16:9, 1:1, etc.), resolutions (1k, 2k, 4k), AI models, and negative prompts to match your creative vision. The Skill accepts these parameters and generates images tailored to your specifications.

What are the limitations when using local API deployments for image generation?▼

The Skill requires a local Jimeng API endpoint and strict parameter discipline—only user-specified options are passed to avoid errors. International and domestic deployments have different endpoint configurations that must be properly configured.

Related Skills

Explore More Design & Creative Skills→
aresbitaresbit
46

openai-image-gen

Generate images from sampled prompts via the OpenAI Images API and save them with a local HTML gallery.

Community
Intermediate
artreimusartreimus

blog-image-cropper

Crop source images into Ylang Labs blog card and header PNG assets.

Community
Intermediate
Randy-C-XRandy-C-X

image-generation

Generate images from natural language prompts with OpenAI or Gemini integration scripts.

Community
Advanced
0xobat0xobat

ai-product-video

Generate product videos from static images using Sora 2, Veo 3.1, and Kling v2.5.

Community
Advanced