⚡

// Skill profile

PoYo Wan 2.6 Video Generation

Name: PoYo Wan 2.6 Video Generation
Author: coolhackboy

name: poyo-wan-2-6

by coolhackboy · published 2026-03-22

图像生成数据处理加密货币

Total installs

Stars

★ 0

Last updated

2026-03

// Install command

$ claw add gh:coolhackboy/coolhackboy-poyo-wan-2-6

View on GitHub

// Full documentation

---

name: poyo-wan-2-6

description: Wan 2.6 video generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `wan2.6-text-to-video`, `wan2.6-image-to-video`, `wan2.6-video-to-video`, text-to-video, image-to-video, video-to-video, and `multi_shots` control.

metadata: {"openclaw": {"homepage": "https://docs.poyo.ai/api-manual/video-series/wan-2-6", "requires": {"bins": ["curl"], "env": ["POYO_API_KEY"]}, "primaryEnv": "POYO_API_KEY"}}

---

# PoYo Wan 2.6 Video Generation

Use this skill for Wan 2.6 jobs on PoYo. It routes between text-to-video, image-to-video, and video-to-video within one model family.

Use When

The user explicitly asks for `Wan 2.6` or one of the `wan2.6-*` model ids.

The task needs one family that covers text-to-video, image-to-video, and video-to-video.

The workflow needs `multi_shots`, resolution control, or source-video transformation.

Model Selection

`wan2.6-text-to-video`: prompt-only video generation.

`wan2.6-image-to-video`: one-image guided video generation.

`wan2.6-video-to-video`: source-video transformation with up to 3 reference videos.

Key Inputs

`prompt` is required.

`image_urls` is only for `wan2.6-image-to-video` and supports one image.

`video_urls` is only for `wan2.6-video-to-video` and supports up to 3 videos.

`duration` supports `5`, `10`, `15`.

`resolution` supports `720p`, `1080p`; `multi_shots` controls single-shot vs multi-shot composition.

Execution

Read `references/api.md` for endpoint details, model ids, key fields, example payloads, and polling notes.

Use `scripts/submit_wan_2_6.sh` to submit a raw JSON payload from the shell.

If the user only needs a curl example, adapt the example from `references/api.md` instead of rewriting from scratch.

After submission, report the `task_id` clearly so follow-up polling is easy.

Output expectations

When helping with this model family, include:

chosen model id

final payload or a concise parameter summary

whether reference images are involved

returned `task_id` if a request was actually submitted

next step: poll status or wait for webhook

// Comments

// Related skills

More tools from the same signal band

Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).

Sign plugins, rotate agent credentials without losing identity, and publicly attest to plugin behavior with verifiable claims and authenticated transfers.

The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your...

日历管理数据处理

1 installs★ 0