jimeng-api

Run `npx skills add iptag/jimeng-api --all -g -y` in your terminal to install the skill globally. You also need the API service running locally via Docker with `docker run -d -p 5100:5100 ghcr.io/iptag/jimeng-api:latest`.

Start the local API service, then ask your AI agent in plain language to generate an image with your session ID. Images are automatically downloaded and saved to your project's /pic folder.

Yes. It supports text-to-image, image-to-image with up to 10 reference images, and text-to-video generation on both the China site and international Dreamina sites.

It supports 1k, 2k, and 4k resolutions with ratios like 1:1, 16:9, 9:16, 4:3, and 21:9. An intelligent ratio mode can auto-pick the best ratio from your prompt.

No. Once the Docker service is running, you simply describe the image you want in plain language and the AI agent handles the API calls and file saving.