higgsfield

Automate Higgsfield image, video, edit, and speech generation via Chrome browser automation.

10|Updated Oct 25, 2025
One-click install
npx skills add https://github.com/fiftynotai/igris-ai --skill higgsfield
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: higgsfield
Source: https://github.com/fiftynotai/igris-ai/tree/main/.claude/skills/higgsfield
Command: npx skills add https://github.com/fiftynotai/igris-ai --skill higgsfield

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the manual, repetitive, and fragile process of producing images, videos, edits, and speech from the Higgsfield web interface by driving Chrome and extracting results so users can get assets without using APIs or repeating UI steps.

Core Features & Use Cases

  • Browser automation: Opens or switches to higgsfield.ai tabs, selects models, enters prompts, and clicks generate using the claude-in-chrome tools.
  • Multi-modal generation: Supports text-to-image, text-to-video, image editing/inpaint, DoP image-to-video, Cinema Studio, speech generation, and specialized mini-app workflows with model selection.
  • File upload and polling: Uploads local reference images, monitors generation progress with configurable timeouts, captures screenshots, and extracts download links or media URLs.
  • Use Case: Produce a 4K photorealistic portrait with Seedream 4.5, animate a still image into a short clip, or generate expressive TTS audio using your logged-in Higgsfield account.

Quick Start

Use the higgsfield skill to generate a photorealistic portrait with seedream 4.5 by saying: /higgsfield seedream photorealistic portrait of a woman in golden hour

Frequently Asked Questions about higgsfield

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate image and video generation on Higgsfield without using an API?

Automate Higgsfield generation by driving the Chrome browser to select models, enter prompts, and extract results using an authenticated higgsfield.ai session, bypassing the need for direct API integration.

Can I generate text-to-speech audio and edit images using browser automation?

Yes, browser automation supports text-to-speech generation and image editing by navigating the Higgsfield web interface to upload files, monitor progress, and extract download links for your media assets.

Do I need a logged-in Higgsfield account to automate video generation in Chrome?

Yes, you need an authenticated higgsfield.ai session in Chrome to automate video generation, as the browser automation tools rely on your active login to access models and generate content.

What is the best way to animate a still image using Higgsfield?

Animate a still image by using browser automation to upload your local reference image to the Higgsfield interface, selecting the appropriate model, and polling the generation progress until the video clip is ready.

How does browser automation handle timeouts when generating 4K photorealistic portraits?

Browser automation handles timeouts by monitoring generation progress with configurable timeout settings, capturing screenshots, and extracting media URLs once the 4K photorealistic portrait generation is complete.

Can I use browser automation to generate content on Higgsfield if I don't know how to code?

Yes, you can use natural language commands to trigger browser automation for Higgsfield, letting the system handle model selection, prompt entry, and result extraction without manual coding.