skills.rest
fuliangtuan
fuliangtuanCOMMUNITY
Explore all skills by this author →
GitHub

jimeng-api

Generate images from text prompts via a local Jimeng API in Docker.

1|Updated Jan 22, 2026
Search Tags:#API#image#docker#local#generate#jimeng
One-click install
npx skills add https://github.com/fuliangtuan/jimeng --skill jimeng-api-fuliangtuan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jimeng-api
Source: https://github.com/fuliangtuan/jimeng/tree/main/jimeng-api
Command: npx skills add https://github.com/fuliangtuan/jimeng --skill jimeng-api-fuliangtuan

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates image generation using a locally deployed Jimeng API service (Docker). It converts text prompts into high-quality images and downloads them to the project's /pic folder. The skill supports text-to-image and image-to-image generation workflows, with configurable aspect ratios and multiple resolution levels.

Core Features & Use Cases

  • Text-to-Image: generate images from text prompts.
  • Image-to-Image: transform existing images with prompts.
  • Local deployment: runs with a Dockerized Jimeng API and saves results to /pic for easy access.

Quick Start

Start the Jimeng API locally (Docker), then run the generation commands:

  • Text-to-image: python scripts/generate_image.py text "a futuristic city at dusk" --session-id YOUR_SESSION_ID
  • Image-to-image: python scripts/generate_image.py image "stylize this photo" --session-id YOUR_SESSION_ID --images /path/to/image.jpg

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 a local Docker API?▼

You can generate images from text prompts locally by running a Dockerized Jimeng API service and executing a Python script with your prompt and session ID. The generated images are automatically downloaded to your project's /pic directory for easy access.

Can I transform an existing image with a text prompt locally?▼

Yes, you can perform image-to-image transformation by running the generation script in image mode. You provide the target image path along with your stylization prompt and session ID, and the local Jimeng API processes the transformation and downloads the result.

Do I need a session ID to use the Jimeng API for image generation?▼

Yes, a valid session ID is required for authentication when using the Jimeng API to generate images. You must pass your specific session ID as a parameter in the generation command to authenticate your local requests.

What resolutions and aspect ratios can I configure for text-to-image generation?▼

The local Jimeng API supports configurable aspect ratios and multiple resolution levels for text-to-image and image-to-image workflows. You can adjust these parameters within the Docker-based setup to match your specific visual content requirements.

Where are the generated images saved after running the Jimeng API script?▼

Generated images are automatically downloaded and saved directly to the project's /pic folder. This ensures that all artwork and visual content produced from your text prompts are stored locally for immediate access.

What dependencies are required to run the local image generation scripts?▼

You need the Python requests and Pillow libraries installed to run the image generation scripts. Additionally, a local Docker environment is required to host the Jimeng API service that processes the text-to-image and image-to-image workflows.

Related Skills

Explore More Software Engineering 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
SJTU-IPADSSJTU-IPADS
7

image-utils

Automate deterministic image editing tasks on image collections with Pillow.

Official
Intermediate
bug-opsbug-ops
55

docker

Automate Docker container and image management workflows.

Community
Advanced
jordanhubbardjordanhubbard
9

nvidia-inference-multimodal

Generate and annotate images using NVIDIA hosted models.

Community
Intermediate