Qwencloud Video Generation

Wraps QwenCloud's Wan video models into a unified workflow: text to video, image to video, keyframe transitions, character role-play, and video editing. The skill handles the async dance (submit, poll, download) and navigates the API's quirks, like kf2v locking you to 5 seconds silent or different resolution parameters across modes. Ships with Python scripts and curl fallbacks, plus guides for prompt structure, duration extensions, and ffmpeg merging. Watch out for model selection: wan2.7 uses different params than 2.6, and the default picks are opinionated. Requires a standard QwenCloud API key, not a Coding Plan key, since video generation isn't available on that tier.

skills.sh installs: 1.7K
GitHub stars: 44
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add qwencloud/qwencloud-ai --skill qwencloud-video-generation --agent claude-code

Installs into .claude/skills of the current project.

Files

Qwen Video Generation

Generate videos using Wan models. All tasks are asynchronous — submit, then poll until completion. This skill is part of qwencloud/qwencloud-ai.

⚠️ Critical Parameter Differences:

kf2v (First+Last Frame): Duration is fixed at 5 seconds — other values will fail. Output is silent only.

Resolution parameters vary by model family, not mode alone: Fetch the current model catalog before choosing size, resolution, or ratio.