higgsfield-generate

Installation
Summary

Generate images and videos across Higgsfield's model suite, plus analyze video virality.

  • Supports 15+ models spanning GPT Image 2 (general graphics), Seedance 2.0 (cinematic video), Nano Banana 2/Pro (character work), Soul variants (identity-consistent stills/video), Kling 3.0, and Marketing Studio for branded ads, product demos, and UGC content
  • Marketing Studio workflows: import products from URL, curate avatars (preset or custom), attach hooks/settings, and generate ads in modes like UGC, unboxing, product review, and TV spot
  • Virality Predictor (brain_activity) analyzes finished videos for hook strength, attention, retention, distraction risk, and creative scoring; returns text report plus visual dashboard
  • Media flags accept local file paths or UUIDs; CLI auto-uploads and auto-detects job vs upload IDs. Chain with higgsfield-soul-id for face consistency across generations
  • All commands block until completion with --wait; no polling required
SKILL.md

Higgsfield Generate

Submit jobs to any Higgsfield model. Wraps the higgsfield CLI. Covers generic image/video/3D/audio generation, Marketing Studio (branded ads, avatars, products, hooks, settings), and, secondarily, Virality Predictor video scoring.

Step 0 — Bootstrap

Before any other command:

  1. If higgsfield is not on $PATH, install it:
    curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
    
  2. If higgsfield account status fails with Session expired / Not authenticated, ask the user to run higgsfield auth login (interactive) and wait for confirmation.

UX Rules

Installs
69.6K
GitHub Stars
481
First Seen
May 4, 2026
higgsfield-generate — higgsfield-ai/skills