skills.rest
MoizIbnYousaf
MoizIbnYousafCOMMUNITY
Explore all skills by this author →
Website𝕏@MoizIbnYousafGitHub

higgsfield-generate

Generates images and videos through the Higgsfield CLI across 30+ AI models.

31|5|Updated Mar 12, 2026
Search Tags:#image generation#avatars#seedance#ai video generation#higgsfield#ugc ads#marketing studio
One-click install
npx skills add https://github.com/MoizIbnYousaf/marketing-cli --skill higgsfield-generate-moizibnyousaf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: higgsfield-generate
Source: https://github.com/MoizIbnYousaf/marketing-cli/tree/main/skills/higgsfield-generate
Command: npx skills add https://github.com/MoizIbnYousaf/marketing-cli --skill higgsfield-generate-moizibnyousaf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @higgsfield/cli, and includes references (resource) components.

What problem does it solve? Creating AI-generated images and videos requires choosing the right model, formatting media inputs correctly, and managing authentication and job polling. This Skill wraps the Higgsfield CLI so an agent can submit generation jobs to 30+ models (Soul V2, Seedance 2.0, Kling 3.0, Veo 3.1, GPT Image 2, Nano Banana 2) and produce branded Marketing Studio ads without manual CLI expertise. ## Core Features & Use Cases - Model routing and selection: Picks the right image or video model based on intent (cinematic stills, UGC ads, character work, fast drafts) using a built-in decision workflow and model catalog reference. - Marketing Studio ads: Generates branded ad videos and images with preset or custom avatars, products imported from URLs, and modes like ugc, tv_spot, unboxing, and virtual try-on. - Media input handling: Accepts local file paths or UUIDs for reference images, start/end frames, video, and audio, with automatic upload and role validation per model. - Use Case: A marketer asks for a 15-second vertical UGC ad from a Shopify product URL. The Skill fetches the product, picks a preset avatar, submits a marketing_studio_video job with --wait, and returns the result URL. ## Quick Start Ask the agent to generate a 15-second vertical UGC marketing video from your product URL using Higgsfield, and it will handle model selection, submission, and return the result URL.

Frequently Asked Questions about higgsfield-generate

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

FAQPage Schema
How do I generate an AI video with Higgsfield?▼

Run higgsfield generate create with a video model such as seedance_2_0, a prompt, and the --wait flag so the command blocks until completion and prints the result URL. Media flags like --start-image accept local paths or UUIDs directly.

How do I create a UGC ad video from a product URL?▼

Use the Marketing Studio flow: run higgsfield marketing-studio products fetch --url to import the product, then submit marketing_studio_video with --url, --mode ugc, and --wait. The backend dedupes by URL and reuses the fetched product entity.

Which Higgsfield model should I use for image generation?▼

GPT Image 2 is the default for high-fidelity general images, graphic design, and text rendering. Use Nano Banana 2 for character or cartoon work, Soul 2.0 for fashion editorial, Soul Location for environments, and Z Image for fast cheap drafts.

Does Higgsfield generation work without the CLI installed?▼

No, the @higgsfield/cli binary and an authenticated account are required. Install via the curl install script and run higgsfield auth login. For one-off images only, the skill can route to the free Gemini-based image-gen fallback instead.

Why does Seedance 2.0 reject the --generate-audio flag?▼

Seedance 2.0 does not declare generate_audio in its schema, so the flag silently breaks. Pass audio through the media role instead with --audio <path> for lipsync or soundtrack matching; --generate-audio is only valid for marketing_studio_video.

When should I not use this skill for product images?▼

Route branded product photoshoots (Pinterest pins, hero banners, virtual try-on) to higgsfield-product-photoshoot, which applies mode-specific prompt enhancers on top of GPT Image 2. Use higgsfield-soul-id instead when training a reusable face identity.

Related Skills

Explore More Marketing & Sales Skills→
Buntyarora97Buntyarora97

branding-generator

Create brand identity kits with color palettes, typography, and logo concepts.

Community
Advanced
indranilbanerjeeindranilbanerjee
726

content-engine

Generate and optimize marketing content across SEO, ads, emails, social, and landing pages.

Community
Intermediate
qwwiwiqwwiwi
3

higgsfield-soul-id

Train a reusable Soul identity model from face photos for consistent generation.

Community
Intermediate
BishopCodesBishopCodes
1

Remotion

Create and render videos programmatically with React and Remotion.

Community
Advanced