higgsfield-generate
Submit generation jobs to Higgsfield's suite of AI models for images, video, 3D assets, and audio. Routes to specialized defaults like GPT Image 2 for design, Seedance 2.0 for video, and Seed Audio 1.0 for sound, with support for Marketing Studio ads, Virality Predictor video scoring, and image-to-3D workflows. Chain with higgsfield-soul-id for consistent identity across outputs.
Higgsfield Generate submits jobs to Higgsfield's AI models for creating images, videos, 3D assets, and audio.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
Higgsfield Generate submits jobs to Higgsfield's AI models for creating images, videos, 3D assets, and audio. Submit generation jobs to Higgsfield's suite of AI models for images, video, 3D assets, and audio. Routes to specialized defaults like GPT Image 2 for design, Seedance 2.0 for video, and Seed Audio 1.0 for sound, with support for Marketing Studio ads, Virality Predictor video scoring, and image-to-3D workflows. Chain with higgsfield-soul-id for consistent identity across outputs.
Use it when
- Yes.
- Yes.
Verify before relying
Read SKILL.md below before installing (13 files). Open directory: indexed for reading, not audited.
Install
higgsfield-ai/skills/higgsfield-generate · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What can higgsfield-generate create?
higgsfield-generate submits generation jobs to Higgsfield's suite of AI models for images, video, 3D assets, and audio. The skill routes to specialized defaults like GPT Image 2 for design, Seedance 2.0 for video, and Seed Audio 1.0 for sound, with support for Marketing Studio ads, Virality Predictor video scoring, and image-to-3D workflows.
Can I make a video from text with higgsfield-generate?
Yes. higgsfield-generate routes text-to-video requests to Seedance 2.0, its specialized video generation model. You can submit text prompts and the skill will generate video content through this dedicated pipeline.
Does higgsfield-generate support branded marketing content?
Yes. higgsfield-generate includes Marketing Studio for creating branded marketing content and product advertisements. It can generate ads, product showcases, and marketing materials tailored to your brand needs.
How does higgsfield-generate handle image-to-video conversion?
higgsfield-generate transforms existing media including image-to-video conversion through its specialized video models. You can upload images and convert them to video animations using the Seedance 2.0 pipeline.
Can higgsfield-generate analyze video performance?
Yes. higgsfield-generate includes Virality Predictor for analyzing video performance and virality potential. Submit your videos to receive scoring and performance insights.
What audio capabilities does higgsfield-generate offer?
higgsfield-generate routes audio requests to Seed Audio 1.0 for text-to-audio generation and sound effect creation. You can generate music, voiceovers, and sound effects through this specialized audio model.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
version: 0.12.0
name: higgsfield-generate
description: |
Generate images/videos/3D assets/audio via Higgsfield AI. Defaults:
GPT Image 2 for image/design/text, Seedance 2.0 for
video, Nano Banana 2/Lite/Pro for character/reference
images, Marketing Studio for ads, Seed Audio 1.0 for audio.
Use when: "generate an image", "make a video", "animate
this photo", "image-to-video", "edit/stylize/remix this
image", "reframe this video", "edit this video from a
sketch", "create a 3D model/GLB", "create a sound effect",
"make music", "text-to-audio", "create an ad", "make a UGC
video", "unboxing", "presenter video", "import product from
URL", or "analyze video virality". Supports image-to-3D
(multi_image_to_3d),
text-to-audio/music (seed_audio), workflow generation
(draw_to_video, reframe), Marketing Studio, and
Virality Predictor (brain_activity).
Chain with higgsfield-soul-id for face/identity consistency.
NOT for: Soul training, photoshoots, cards, explainers (use
higgsfield-video-explainer), playable games/assets (use
higgsfield-game-generation), or TTS.
argument-hint: "[prompt-or-analysis-request] [--model <name>] [--image|--video
(truncated - see the full file via the links below)
File tree — 13 files
higgsfield-generate/SKILL.md
higgsfield-generate/references/marketing-ad-references.md
higgsfield-generate/references/marketing-avatars.md
higgsfield-generate/references/marketing-brand-kits.md
higgsfield-generate/references/marketing-dtc-ads.md
higgsfield-generate/references/marketing-modes.md
higgsfield-generate/references/marketing-products.md
higgsfield-generate/references/marketing-setup-items.md
higgsfield-generate/references/media-inputs.md
higgsfield-generate/references/model-catalog.md
higgsfield-generate/references/prompt-engineering.md
higgsfield-generate/references/troubleshooting.md
higgsfield-generate/references/workflows.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate images, videos, 3D models, or audio using AI models”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Higgsfield bundles five integrated skills for creative generation: produce images and videos across 30+ models, train reusable face identities, create branded product photography and marketplace cards, score video virality, and build full-stack websites. Each skill chains together—train a Soul Character once, then reference it across generation jobs, or use product-photoshoot and marketplace-cards for e-commerce visuals with backend prompt enhancement.
Create full-featured web games from concept to deployment, or generate individual game assets like sprites, textures, animations, and audio. The skill handles the complete pipeline—from design planning through asset generation to browser deployment—supporting solo, local multiplayer, and online multiplayer modes.
Higgsfield Video routes your requests to 11 official AI video models—including Sora 2, Google Veo 3, Kling variants, Seedance Pro, and Cinema Studio 3.5—automatically selecting the best fit for your use case. It supports text-to-video and image-to-video workflows, applies 6 video presets (UGC, Unboxing, Product review, Hyper motion, TV spot, Wild Card), handles character consistency with Kling Avatars 2.0, and manages async job polling until your video is ready.
Higgsfield Image calls Higgsfield MCP's generation tools to produce finished images from single-line prompts. It automatically selects from 11 official models (Soul 2.0, GPT Image 2, Flux Kontext, Seedream 4.0, Nano Banana Pro, and others), handles character consistency via Soul Characters, applies style presets and resolution scaling (720p through 4K), and manages async job polling.
Higgsfield Soul ID creates a reusable identity model trained on your face photos, enabling consistent self-representation across Higgsfield's image and video generation tools. Submit 5–20 photos with varied angles and lighting, then reference your trained Soul in downstream generation tasks using the returned ID.
This skill orchestrates a complete pipeline for creating photorealistic user-generated content ads in 15-second vertical format. It combines script generation, AI creator face synthesis, and multi-shot video production to deliver ads that feel genuinely human-made rather than AI-generated. The workflow guides you through collecting product details and reference videos, then chains together specialized tools to produce authentic-looking UGC content.
More skills Seedance Auto Generate (unlicensed) · Higgsfield Operator (unlicensed) · Ugc Video Auto (unlicensed) · Higgsfield Image Auto (unlicensed) · agnes-ai-generation (MIT) · Ugc Hot Girl (unlicensed) · higgsfield-product-photoshoot (MIT)