higgsfield-video
Produce video (and its supporting stills) through Higgsfield (higgsfield.ai), a multi-model creative platform that fronts third-party video models (Kling, Veo, Seedance, Wan, MiniMax, and, until retirement, Sora) plus Higgsfield's own control layer — Soul / Soul ID image generation, the DoP camera-preset engine, and the Cinema Studio filmmaking suite. Use this skill when a request routes generation through Higgsfield specifically, when the user wants aggregator-level model switching and cinematic camera/effect presets in one workspace, when planning character consistency via Soul ID, or when d
Profile →npx skills add calesthio/generative-media-skills --skill higgsfield-video --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Produces video (and its supporting stills) through Higgsfield, a multi-model creative platform that fronts third-party video models and adds an in-house control layer (Soul, Soul ID, DoP, Popcorn, Cinema Studio). It covers model selection, per-model prompt strategy, credit economics, API surface, capability limits, and rights/consent policies for generated and uploaded real-person footage.
How it works
- Higgsfield acts as an aggregator fronting multiple video models (Kling, Veo, Seedance, Wan, MiniMax, Sora) plus in-house layers (Soul/Soul ID, DoP, Popcorn, Cinema Studio).
- It guides model selection based on the task: multi-model side-by-side evaluation, character consistency via Soul ID, and cinematic control via DoP/Cinema Studio.
- DoP provides camera-movement presets; Cinema Studio orchestrates multi-shot rigs, model routing, and sequence continuity.
- Soul ID trains an identity layer from multiple photos to lock character identity across prompts and presets; identities stay within Higgsfield's ecosystem.
- Prompt strategy varies by underlying model; the skill instructs how to tailor prompts to Seedance 2.0, Kling 3.0, Veo 3.1, Wan 2.7, MiniMax/Hailuo, and DoP/Cinema Studio usage.
- Credit economics are managed per model, resolution, and duration, with tier-based credits, top-up packs, and non-rolling credits; pricing and terms are volatile and should be verified live.
When to use it
- Route through Higgsfield when you want side-by-side model switching and cinematic control in one workspace.
- Use when you need Soul ID character consistency and/or need DoP/Cinema Studio for multi-shot rigs.
- Choose Higgsfield when deciding whether to go through Higgsfield versus a direct model provider, or when unified credit handling and policy enforcement across models is desired.
What it can touch
- Models fronted by Higgsfield: Kling 3.0, Kling 2.6, Kling o1, Seedance 2.0, Veo 3.1, Wan 2.7, MiniMax (Hailuo 2.3), Sora 2 (retired).
- In-house controls: Soul / Soul 2.0, Soul ID, DoP, Popcorn, Cinema Studio.
- Supporting image models in the same workspace: Seedream 4.x, Flux.2 Pro, Nano Banana / Nano Banana Pro, GPT Image.
- It describes per-model prompts, credits, and rights/consent policies for generated and uploaded footage.
Caveats
- Sora is retired; treat as unavailable for new production; migrate prompts to Seedance 2.0 or Veo 3.1.
- Model lineup, pricing, and credits are volatile and must be verified live before quoting.
- Aggregator inherits model limits; duration, resolution, audio, and content moderation apply per underlying model, not Higgsfield as a brand.
- Identities via Soul ID stay internal to Higgsfield; not exportable.
- Exact tier names and prices differ between pages and trackers; verify live pricing.
# Higgsfield video ## What Higgsfield is, and the one fact that governs everything Higgsfield (higgsfield.ai) is an **aggregator plus a control layer**. It is not a single model. It is a workspace that: 1. **Fronts third-party video models** you could otherwise reach directly (Kling, Veo, Seedance, Wan, MiniMax, and — until its shutdown — Sora), and 2. **Adds its own in-house layer** on top: `Soul
What does the higgsfield-video skill do?
Produce video (and its supporting stills) through Higgsfield (higgsfield.ai), a multi-model creative platform that fronts third-party video models (Kling, Veo, Seedance, Wan, MiniMax, and, until retirement, Sora) plus Higgsfield's own control layer — Soul / Soul ID image generation, the DoP camera-preset engine, and the Cinema Studio filmmaking suite. Use this skill when a request routes generation through Higgsfield specifically, when the user wants aggregator-level model switching and cinematic camera/effect presets in one workspace, when planning character consistency via Soul ID, or when d
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill higgsfield-video --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.