skills.rest
ferrarifankid04
ferrarifankid04COMMUNITY
Explore all skills by this author →
GitHub

higgsfield-generate

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

Updated Aug 6, 2026
Search Tags:#image generation#video generation#ugc#text-to-audio#3d assets#higgsfield#ai ads
One-click install
npx skills add https://github.com/ferrarifankid04/ai-skills-public --skill higgsfield-generate-ferrarifankid04
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: higgsfield-generate
Source: https://github.com/ferrarifankid04/ai-skills-public/tree/main/claude-code/skills/higgsfield-generate
Command: npx skills add https://github.com/ferrarifankid04/ai-skills-public --skill higgsfield-generate-ferrarifankid04

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Choosing the right generative AI model and correctly submitting jobs for images, videos, 3D assets, audio, or ad creatives is complex and error-prone. This Skill wraps the Higgsfield CLI with model-routing rules, media-input handling, and validation so generation requests succeed on the first attempt. ## Core Features & Use Cases - Model routing across modalities: Routes prompts to GPT Image 2 for design/text images, 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 using avatars, products, hooks, settings, brand kits, and ad references, including a URL-driven Click-to-Ad flow. - Virality Predictor analysis: Scores finished videos for hook strength, attention, retention, and virality 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 the ugc mode, submits a marketing_studio_video job with --wait, and returns the result URL. ## Quick Start Ask the agent to generate an image or video with a prompt, for example: generate a 12-second cinematic video of a neon city at dusk using Higgsfield.

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 image or video with Higgsfield AI?▼

Run higgsfield generate create with a model ID, a --prompt, and --wait so the command blocks until completion and prints the result URL. Media inputs like --image or --start-image accept local file paths or UUIDs, and paths are auto-uploaded.

Which Higgsfield model should I use for video generation?▼

Seedance 2.0 is the default for serious multi-shot or image-to-video work up to 4K. Use Kling 3.0 for cheaper single-plane scenes, Marketing Studio for ads, and Cinema Studio Video 3.0 for cinema-grade fidelity.

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

Run higgsfield marketing-studio products fetch --url <url> --wait to import the product, then call higgsfield generate create marketing_studio_video with the same --url, a mode like ugc, duration, and aspect ratio. The backend dedupes by URL and reuses the product entity.

Can Higgsfield analyze a video instead of generating one?▼

Yes, the 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. No prompt is required.

Why does my Higgsfield generation fail with unknown params or missing medias?▼

Unknown params means the model schema does not accept that flag; run higgsfield model get <model> to check accepted parameters. Missing required params: medias on brain_activity means you must pass exactly one video with --video.

When should I not use this generation skill?▼

Do not use it for Soul training or photoshoots, narrated explainer videos, playable game assets, or TTS; those route to dedicated skills like higgsfield-soul-id, higgsfield-video-explainer, or higgsfield-game-generation. Brand product photoshoots also belong to higgsfield-product-photoshoot.

Related Skills

Explore More Design & Creative Skills→
leobbaronileobbaroni
1

higgsfield-generate

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

Community
Advanced
El3tar-cmdEl3tar-cmd
18

ad-creative

Generate multi-platform ad creatives from a brief with A/B variants.

Community
Advanced
qwwiwiqwwiwi
3

higgsfield-soul-id

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

Community
Intermediate
eachlabseachlabs
28

eachlabs-product-visuals

Generate e-commerce product photography and videos using AI models.

Official
Intermediate