skills.rest
leobbaroni
leobbaroniCOMMUNITY
Explore all skills by this author →
GitHub

higgsfield-generate

Generate images, videos, 3D assets, and audio through the Higgsfield AI CLI.

1|Updated Jul 19, 2026
Search Tags:#image generation#text-to-audio#ai video generation#higgsfield#3d asset#marketing studio#virality predictor
One-click install
npx skills add https://github.com/leobbaroni/maestro --skill higgsfield-generate-leobbaroni
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: higgsfield-generate
Source: https://github.com/leobbaroni/maestro/tree/main/skills/maestro/library/higgsfield-skills/higgsfield-generate
Command: npx skills add https://github.com/leobbaroni/maestro --skill higgsfield-generate-leobbaroni

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Choosing the right generative AI model and submitting correctly parameterized jobs is error-prone when a platform offers dozens of image, video, 3D, and audio models with different schemas. This Skill routes each creative brief to the right Higgsfield model and submits validated generation jobs through the higgsfield CLI. ## Core Features & Use Cases - Model routing: Maps each brief to a default model — GPT Image 2 for images and design, Seedance 2.0 for video, Nano Banana 2 for character work, Seed Audio 1.0 for audio, and Multi-Image to 3D for GLB assets. - Marketing Studio workflows: Creates branded ad images and UGC videos with avatars, products, hooks, settings, ad references, brand kits, and the DTC Ads Engine. - Virality Predictor: Scores finished videos for hook strength, attention, and retention via the brain_activity job type. - Use Case: A marketer provides a product URL and asks for a 15-second vertical UGC ad; 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 12-second 4K video of a camera dollying into a neon city street using Higgsfield, starting from your reference image.

Frequently Asked Questions about higgsfield-generate

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

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

Run higgsfield generate create with a video model such as seedance_2_0, passing a prompt, optional --start-image, duration, resolution, and --wait to block until the result URL prints. Seedance 2.0 is the default for serious multi-shot or image-to-video work up to 4K.

Which Higgsfield model should I use for image generation?▼

GPT Image 2 is the default for high-fidelity general images, graphic design, and on-image text. Use Nano Banana 2 for character or cartoon work, Recraft V4.1 for logos and vector-style graphics, and Soul Location for environments without people.

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

Fetch the product with higgsfield marketing-studio products fetch --url, then submit marketing_studio_video with the same URL, a mode such as ugc, duration, and aspect ratio. The backend dedupes by URL and reuses the imported product entity.

Can Higgsfield analyze a video instead of generating one?▼

Yes. Virality Predictor (job type brain_activity) takes one video via --video and returns a text report with an overall score, peak hook second, sustain score, and an Open report link. It requires no prompt.

Why does my Higgsfield job fail with unknown params or invalid values?▼

Each model declares a closed schema of parameters and media roles. Run higgsfield model get <model> to inspect allowed values, then pass only declared flags; the CLI rejects unknown params and coerces out-of-range enums with an adjustments note.

When should I not use generic generation in Higgsfield?▼

Route brand identity systems to higgsfield-brandkit, YouTube thumbnails to higgsfield-youtube-thumbnail, narrated explainers to higgsfield-video-explainer, product photoshoots to higgsfield-product-photoshoot, and game assets to higgsfield-game-generation instead of generic generation.

Related Skills

Explore More Design & Creative Skills→
MoizIbnYousafMoizIbnYousaf
31

higgsfield-generate

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

Community
Advanced
techshiv91-celltechshiv91-cell
3

ad-creative

Generate and iterate ad creative across major ad platforms.

Community
Advanced
qwwiwiqwwiwi
3

higgsfield-soul-id

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

Community
Intermediate
mohammedburqanmohammedburqan

higgsfield-generate

Generate images, videos, 3D assets, and audio using Higgsfield AI models.

Community
Advanced