jimeng-api
Generate images using the Jimeng API based on text prompts. Use this skill when users request AI-generated images from the Jimeng (即梦AI) service, artwork, illustrations, or visual content creation. Supports text-to-image and image-to-image generation with customizable ratios and resolutions.
Security Assessment
About jimeng-api
The jimeng-api skill allows users to generate high-quality images using the Jimeng API. This skill enables seamless conversion of text descriptions into images, as well as image transformations based on provided visual inputs. By integrating with a locally deployed Jimeng API service, it provides an efficient method for creating artwork, illustrations, and visual content. The skill operates with the convenience of automatic image downloads to a predefined directory, simplifying workflows for creative and design tasks. Whether you need to generate fresh visual content or transform existing images, this skill is tailored for quick and customizable image creation.
FAQ
How do I use the jimeng-api skill?
To use this skill, you must first deploy the Jimeng API locally via Docker. Then, provide the required Session ID and specify the parameters like text prompts or images to generate. The skill supports text-to-image and image-to-image generation with customizable resolutions and aspect ratios.
What are the system requirements for running this skill?
The skill requires Python 3.7 or higher, along with the dependencies requests (version 2.28.0 or higher) and Pillow (version 9.0.0 or higher). The Jimeng API must also be running locally via Docker.
Can I use the skill without a Session ID?
No, a valid Session ID is required to access the Jimeng API. Make sure to get your Session ID from the Jimeng website and provide it when prompted by the skill.
Are there any restrictions on image resolutions?
Yes, different regions have different resolution restrictions. For example, the US site has a fixed 1024x1024 resolution with 2k quality, while other regions like HK, JP, and SG support 1k resolution but allow custom aspect ratios.
What models can I use for image generation?
The default model is 'jimeng-4.0', but you can specify other models like 'jimeng-3.1' based on your requirements. Ensure you check the region-specific capabilities before selecting a model.
Install jimeng-api
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
iptag/jimeng-api