jimeng-free-api-all  by wwwzhouhui

OpenAI-compatible API for advanced AI media generation

Created 5 months ago
376 stars

Top 75.9% on SourcePulse

GitHubView on GitHub
Project Summary

This project provides an OpenAI-compatible API server for accessing Jimeng AI's powerful image and video generation capabilities. It targets developers seeking to integrate advanced AI media generation into their applications without complex setup, offering a free, zero-configuration solution with daily usage limits.

How It Works

This project reverse-engineers the Jimeng AI service, encapsulating its image and video generation models (including text-to-image, image-to-image, and various video generation techniques) behind an API that mirrors OpenAI's structure. It utilizes Node.js and Koa for the backend, with Docker support for streamlined deployment. The core novelty lies in abstracting the proprietary Jimeng AI service into a developer-friendly, standardized API format, accessible via a user-provided sessionid.

Quick Start & Requirements

Installation is recommended via Docker using the wwwzhouhui569/jimeng-free-api-all:latest image, or by building from source with Node.js (≥16.0.0) and npm/yarn. A critical prerequisite is obtaining a sessionid from the official Jimeng AI website (https://jimeng.jianying.com/) by inspecting browser cookies. Multiple sessionids can be configured for redundancy.

Highlighted Details

  • OpenAI Compatibility: Offers endpoints like /v1/chat/completions, /v1/images/generations, and /v1/videos/generations.
  • Model Support: Integrates multiple models including jimeng-5.0-preview, jimeng-4.6 for image generation, and jimeng-video-3.5-pro, seedance-2.0 for video.
  • Generation Capabilities: Supports text-to-image, image-to-image, text-to-video, image-based video generation, and multi-image video synthesis.
  • High Resolution: Capable of generating images up to 4K resolution and videos up to 1080p.

Maintenance & Community

Recent updates (e.g., v0.8.0 on 2026-02-09) indicate active development, with recent additions of new image generation models. Direct contact information for the author (WeChat, Email) is provided for inquiries.

Licensing & Compatibility

The project is released under the MIT License. However, a significant restriction is explicitly stated: "For personal use only, prohibited for external services or commercial use." This limits its applicability for business or public-facing applications despite the permissive license.

Limitations & Caveats

As a reverse-engineered API, its stability is not guaranteed and is dependent on upstream changes by Jimeng AI. The requirement for a valid sessionid necessitates manual retrieval and management, as these tokens expire. The project explicitly forbids commercial use or offering it as a service, and users risk account blocking by Jimeng AI if these terms are violated.

Health Check
Last Commit

2 days ago

Responsiveness

Inactive

Pull Requests (30d)
1
Issues (30d)
10
Star History
161 stars in the last 30 days

Explore Similar Projects

Starred by Pawel Garbacki Pawel Garbacki(Cofounder of Fireworks AI), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
2 more.

gpt4free by xtekky

0.1%
66k
API package for multi-provider LLM requests (GPT-4.1, Gemini 2.5, Deepseek R1)
Created 2 years ago
Updated 1 day ago
Feedback? Help us improve.