# iptag/jimeng-api

Reverse-engineered the official API for Jimeng/Dreamina’s text-to-image and image-to-image features. Drew inspiration from several experts’ projects and made some tweaks, which significantly improved stability.

Repository: https://github.com/iptag/jimeng-api
Canonical: https://ross.abutalabs.com/products/jimeng-api
Language: TypeScript
License: GPL-3.0
License Family: copyleft
Topics: image-to-image, jimeng, text-to-image, unofficial-api, api-reverse-engineering, dreamina
Archived: true
Last push: 2026-03-02T04:28:43+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 72, longevity 24
- inputs: {"age_days": 339, "days_push": 184, "days_rel": 184, "gap_med": 1.0, "n_releases_24m": 51}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1041, forks 308 (observed 2026-08-28T04:03:20.663083+00:00)

## What it is
A self-hosted API service that reverse-engineers Jimeng AI (China) and Dreamina (international) to expose free AI image and video generation endpoints. It supports text-to-image, image-to-image, and text-to-video generation with Docker deployment and OpenAI-style API routes.

## Use cases
- generate AI images from text prompts for free
- convert text descriptions into videos
- transform existing images with image-to-image synthesis
- self-host an OpenAI-compatible image generation API
- access Jimeng/Dreamina models programmatically
- generate 2K or 4K resolution AI artwork

## When to choose
- you want free access to Jimeng/Dreamina image and video generation via API
- you need an OpenAI-compatible images endpoint backed by Jimeng models
- you want a Dockerized self-hosted generation service with polling and retry logic

## When to avoid
- you need a officially supported, ToS-compliant image generation API
- you require production reliability or SLAs, since the unofficial API can break or cause account bans
- you need models other than Jimeng/Dreamina

## Facets
- artifact type: service
- maturity: active
- function: image-processing, http-server, api-framework, llm-inference
- domain: artificial-intelligence, image-processing, apis, reverse-engineering
- platform: self-hosted, cross-platform
- tags: text-to-image, image-to-image, text-to-video, dreamina, jimeng, unofficial-api, api-reverse-engineering, openai-compatible, video, nodejs, docker

## Member repositories
- iptag/jimeng-api (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.663083+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:02:57.086441+00:00, confidence not recorded.
  - readme: https://github.com/iptag/jimeng-api (fetched 2026-08-28T04:03:20.663083+00:00, sha 51cd0441bbff)
- Data as of 2026-08-30T08:39:29.467469+00:00.