vidu-video
Plan and integrate ShengShu Vidu Open Platform video generation with current model/mode selection, reference consistency, pricing, exact approval, async task handling, and safe artifact custody. Use for Vidu API text-to-video, image-to-video, start/end-frame, multi-subject reference, media-reference, or Q2 multi-frame work; do not conflate the API with vidu.com consumer plans or Vidu-S1 streaming digital humans.
Profile →npx skills add calesthio/generative-media-skills --skill vidu-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
Designs a production request or integration for the Vidu Open Platform API, defaulting to dry-run planning and preventing submission of paid generation, private-media uploads, task cancellations, or downloads until exact provider, endpoint, model, inputs, request digest, maximum charge, storage destination, and disclosure plan are approved.
How it works
The skill maintains separation between surfaces: it treats the Open Platform API (https://api.vidu.com) as the surface to use, and distinguishes it from the consumer product and Vidu-S1. It emphasizes choosing a mode first (endpoint) and then a model, with a table of endpoint options and production-safe choices. It requires explicit confirmation of transport details and adherence to pricing, credits, and audio controls per model. It provides multiple complete example payloads using models like viduq3-turbo, viduq3-pro, and viduq3-mix, including constraints such as duration, resolution, aspect ratio, audio, seed, and payload. It documents how to construct input manifests, hash guidance, and the need for an approval record containing provider, endpoint, model, mode, duration, resolution, audio, input and request hashes, and execution manifest hash.
When to use it
Use when planning or integrating a Vidu Open Platform API-based video generation request, ensuring operator approval of provider, endpoint, model, inputs, and cost before execution. Default behavior is dry-run planning and avoidance of any paid generation until explicit approval is obtained.
What it can touch
Open Platform API surface: https://api.vidu.com, API keys, organization limits, asynchronous tasks, and API credits. Requires explicit approval of endpoint, model, inputs, and pricing before performing any real generation.
Caveats
Models, prices, accepted fields, policies, and availability are volatile; re-open the linked endpoint and pricing pages immediately before execution. The surface details, transport, and pricing must be confirmed with Vidu support or in the signed-in console prior to making a real request.
# Vidu video Use this skill to design a production request or integration for the **Vidu Open Platform API**. Default to dry-run planning. Never submit a paid generation, upload private media, cancel a task, or download a result until the operator has approved the exact provider, endpoint, model, inputs, request digest, maximum charge, storage destination, and disclosure plan. This document was ve
What does the vidu-video skill do?
Plan and integrate ShengShu Vidu Open Platform video generation with current model/mode selection, reference consistency, pricing, exact approval, async task handling, and safe artifact custody. Use for Vidu API text-to-video, image-to-video, start/end-frame, multi-subject reference, media-reference, or Q2 multi-frame work; do not conflate the API with vidu.com consumer plans or Vidu-S1 streaming digital humans.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill vidu-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.