---
title: "Higgsfield CLI (Marketing Studio) — how to use it for AI video"
description: "Official Higgsfield CLI: 40+ image and video models plus marketing-studio branded ads and a Virality Predictor. Install in Claude Code, Codex and Grok with one command."
url: https://varg.ai/how-to/skills/higgsfield-cli-marketing-studio
updated: 2026-10-29
---

# Higgsfield CLI (Marketing Studio) — model skill for ads & UGC

> **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page. From a terminal: `curl -fsSL https://varg.ai/install | sh` installs the vargai CLI (https://varg.ai/how-to/cli.md): `vargai search` and `vargai install <slug>` with no key, every varg model after `vargai login`.

Official Higgsfield CLI: 40+ image and video models plus marketing-studio branded ads and a Virality Predictor.

- **Type:** [Model](https://varg.ai/how-to/models.md) · [Ads & UGC](https://varg.ai/how-to/browse/skills/ads.md)
- **Slug:** `higgsfield-cli-marketing-studio`
- **Status:** live
- **Publisher:** Higgsfield AI (vendor)
- **License:** MIT
- **Source:** https://github.com/higgsfield-ai/cli
- **Works in:** Claude Code, Codex, Cursor, Gemini CLI, OpenClaw
- **Requires:** Higgsfield account and credits
- **Adoption:** 688 GitHub stars (GitHub, 2026-10-29)

## What it does

Terminal access to Higgsfield's models (Nano Banana Pro, Seedance 2.5, Kling v3.0, Veo 3.1, Soul V2, FLUX.2). `higgsfield marketing-studio` builds branded ads from avatars, products, ad references, brand kits and ad formats (DTC Ads Engine), `product-photoshoot` makes product images and the Virality Predictor scores finished videos. Agents call it straight from the shell.

## Use when

- branded UGC or DTC ads from product + avatar
- score a video's virality before launch
- batch product photos for ads

## Not for

- free generation

## Install

- Claude Code: `npm install -g @higgsfield/cli`
- Codex: `npm install -g @higgsfield/cli`
- Cursor: `npm install -g @higgsfield/cli`
- OpenClaw: `npm install -g @higgsfield/cli`
- Gemini CLI: `npm install -g @higgsfield/cli`
- Any agent, with the vargai CLI: `vargai install higgsfield-cli-marketing-studio`

**Models it drives:** Nano Banana Pro, Seedance 2.5, Kling v3.0, Veo 3.1, Soul V2, FLUX.2

## More ads & UGC skills

- [Ecommerce video ad skills for Claude Code and AI agents](https://varg.ai/how-to/skills/ecommerce-video-ads.md): Product videos that sell on TikTok, TikTok Shop, Reels and Meta: angle, hook, format, script, rules, variants.
- [Turn a product into scroll-stopping video hooks](https://varg.ai/how-to/skills/product-video-hooks.md): The first 3 seconds of a product video: frame, line and text that agree, from a 70-line hook bank.
- [Open-source alternative to Arcads: AI UGC ads](https://varg.ai/how-to/skills/ai-ugc-ad-video.md): AI UGC ads with an AI actor holding your real product: face, voice and label locked, labelled.
- [Turn one winning ad into a creative testing plan](https://varg.ai/how-to/skills/ad-creative-testing.md): How many ads to test, what to change, when to judge, kill or scale — concepts Meta sees as different.
- [Turn a product into a dropshipping guide reel](https://varg.ai/how-to/skills/varg-dropship-reel.md): The faceless "comment GUIDE" reel: product hook, a marker pointing at cost and price on a laptop, a skyline ending.
- [Turn product photos into a viral product hook](https://varg.ai/how-to/skills/varg-product-hook.md): Find a hook that already sells, then remake it with your product as phone or security-cam footage on Seedance 2.5.

## Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

- Any agent with a terminal: `curl -fsSL https://varg.ai/install | sh` (Windows: `irm https://varg.ai/install.ps1 | iex`), then `vargai login` and every model is a command — `vargai generate_video …`, `vargai estimate_cost …` (https://varg.ai/how-to/cli/)
- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Grok and any agent that reads SKILL.md: `npx skills add vargHQ/skills --skill varg-ai`, or point it at the skill's SKILL.md
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt