Connect Higgsfield AI to Your AI Agent

Describe the image you want, or provide a public image URL and a motion prompt to animate it.

4 tools API key

Try a Higgsfield AI Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill Higgsfield AI

Generate an Image

Submit a visual prompt and retrieve output links after the job finishes.

/oo Higgsfield AI: Generate an image of [scene] with Higgsfield model [model ID], aspect ratio [ratio], and resolution [resolution]. Check its request status and give me the completed image links.

Animate a Source Image

Use an existing image and motion instructions to create a video.

/oo Higgsfield AI: Animate this public image [URL] using model [model ID] for [duration] seconds with this motion: [instructions]. Check status and provide the video link when complete.

Start Working with Higgsfield AI

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect Higgsfield AI

Connect a paired Higgsfield API key and API secret from the Cloud dashboard.
Connect Higgsfield AI →
Give Your Agent a Task

Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →

Choose Your Agent

Codex Claude Code Cursor Hermes

Higgsfield API access for the selected model.
Image-to-video requires a publicly accessible source image URL. A request ID means the job was submitted, not that generation finished.

Higgsfield AI Tools

Higgsfield accepts text-to-image and image-to-video requests with model-specific options. Generation is asynchronous; status lookup provides images or video when available.

Image and Video Requests

Submit image generation or image-to-video jobs with prompts and selected model options.

Request Status and Cancellation

Read generation state and available output links, or request cancellation of a queued job.

4 tools

Submit Image Generation

Submit a Higgsfield text-to-image generation request.

higgsfield_ai.submit_image_generation

Submit Video Generation

Submit a Higgsfield image-to-video generation request.

higgsfield_ai.submit_video_generation

Get Request Status

Retrieve the current status and outputs for a Higgsfield generation request.

higgsfield_ai.get_request_status

Cancel Request

Cancel a queued Higgsfield generation request.

higgsfield_ai.cancel_request

Frequently Asked Questions

Can I upload a local image directly?

The video action takes a publicly accessible image URL. Make the source image available at such a URL before submitting the request.

Can I choose a model?

Yes. Provide a model ID and options accepted by that model. Additional model-specific arguments can be supplied when needed.

When is the output ready?

Check the submitted request’s status. Completed requests expose available image or video outputs; a submission response alone is not completion.