skills.rest
LupinLin1
LupinLin1COMMUNITY
Explore all skills by this author →
GitHub

jimeng-api

Generate images and videos via the Jimeng API with configurable parameters.

Updated Aug 23, 2026
Search Tags:#image-generation#text-to-image#video-generation#ai-art#text-to-video#jimeng#omni-reference
One-click install
npx skills add https://github.com/LupinLin1/jimeng --skill jimeng-api-lupinlin1
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jimeng-api
Source: https://github.com/LupinLin1/jimeng/tree/main/jimeng-api
Command: npx skills add https://github.com/LupinLin1/jimeng --skill jimeng-api-lupinlin1

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provides a reliable, script-driven interface to generate high-quality AI images and videos from prompts and reference media, removing manual steps of API interaction, file uploads, and result retrieval for creative and automation workflows.

Core Features & Use Cases

  • Text-to-Image and Image-to-Image: Generate images from text prompts or transform existing images, with configurable aspect ratio and resolution.
  • Async Video Generation: Submit text-to-video, image-to-video, first+last frame, or omni-reference jobs that return task IDs for polling and later download.
  • Multipart Uploads and Omni Reference: Support local file uploads and mixed media references (images, videos, audio) for advanced Seedance workflows.
  • Operational Safety and Outputs: Requires a Session ID for authentication, saves images to a project pic folder and videos to a vid folder, and includes error messages and troubleshooting guidance.

Quick Start

Use the jimeng-api skill to generate a 5 second video from the prompt "a cinematic sunrise over mountains" using your Session ID.

Frequently Asked Questions about jimeng-api

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

FAQPage Schema
How do I generate AI videos from text prompts using an API?▼

To generate AI videos from text prompts, you submit an asynchronous text-to-video task via API using your Session ID, which returns a task ID for polling until the video finishes processing and downloads.

How does image-to-image generation work with local files?▼

Image-to-image generation works with local files by using multipart uploads to transfer your reference media to the API, allowing the AI to transform existing images based on your configured prompt and resolution parameters.

Do I need a Session ID to use the Jimeng API for media generation?▼

Yes, you need a valid Session ID for authentication to use the Jimeng API, as it ensures operational safety and authorized access when submitting text-to-image, video generation, or omni-reference jobs.

Can I use multiple reference images and videos for a single generation task?▼

Yes, you can use mixed media references including images, videos, and audio for advanced Seedance workflows through the omni-reference feature, enabling complex prompt-driven media generation.

Where are the generated images and videos saved after API processing?▼

Generated images are saved to a designated project pic folder, and videos are saved to a vid folder, ensuring organized local outputs after the asynchronous API polling retrieves the finished assets.

What is the best way to automate text-to-image generation for design pipelines?▼

The best way to automate text-to-image generation is using a script-driven API interface that accepts configurable model, aspect ratio, and resolution parameters, removing manual upload and retrieval steps.

Related Skills

Explore More Design & Creative Skills→
payrocpayroc

add-attachment-to-processing-account

Upload documents to Payroc processing accounts via the Boarding API.

Official
Advanced
freestyleflyfreestylefly
869

seedance

Generate AI videos from prompts and reference images via Seedance CLI.

Community
Advanced
toanalientoanalien

media-processing

Convert media formats and remove image backgrounds using FFmpeg, ImageMagick, and RMBG CLI.

Community
Advanced
wwwzhouhuiwwwzhouhui
259

jimeng_mcp_skill

Generate images and videos from text and existing media via Jimeng MCP server.

Community
Advanced