{"skill":{"slug":"poyo-grok-imagine","displayName":"Grok Imagine API","summary":"Use PoYo AI Grok Imagine Video for short text-to-video and image-to-video generation with motion-style controls through the `https://api.poyo.ai/api/generate...","description":"---\nname: poyo-grok-imagine\ndescription: Use PoYo AI Grok Imagine Video for short text-to-video and image-to-video generation with motion-style controls through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants 6s or 10s clips, optional `mode` styling, or PoYo payloads for `grok-imagine`.\nmetadata: {\"openclaw\": {\"homepage\": \"https://docs.poyo.ai/api-manual/video-series/grok-imagine\", \"requires\": {\"bins\": [\"curl\"], \"env\": [\"POYO_API_KEY\"]}, \"primaryEnv\": \"POYO_API_KEY\"}}\n---\n\n# PoYo Grok Imagine Video Generation\n\nUse this skill to submit and track PoYo jobs for the Grok Imagine Video family.\n\n## Quick workflow\n\n1. Choose the right model id for the requested output.\n2. Build the request body for `POST https://api.poyo.ai/api/generate/submit`.\n3. Send Bearer-authenticated JSON with `Authorization: Bearer <POYO_API_KEY>`.\n4. Save the returned `task_id`.\n5. Poll unified task status or wait for `callback_url` notifications.\n\n## Request rules\n\n- Require top-level `model`.\n- Keep prompts concrete and outcome-focused.\n- Require `input.prompt` unless the user already supplied a full payload.\n- Use `input.image_urls` only when the task needs reference or source images.\n- Use `input.duration` when the clip length matters.\n- Use `input.aspect_ratio` when the output surface matters.\n\n## Model selection\n\n### `grok-imagine`\n\nUse for general generation with this model variant.\n\n## Execution\n\n- Read `references/api.md` for endpoint details, model ids, key fields, example payloads, and polling notes.\n- Use `scripts/submit_grok_imagine.sh` to submit a raw JSON payload from the shell.\n- If the user only needs a curl example, adapt the example from `references/api.md` instead of rewriting from scratch.\n- After submission, report the `task_id` clearly so follow-up polling is easy.\n\n## Output expectations\n\nWhen helping with this model family, include:\n- chosen model id\n- final payload or a concise parameter summary\n- whether reference images are involved\n- returned `task_id` if a request was actually submitted\n- next step: poll status or wait for webhook\n\nNotes:\n\nNeeds POYO_API_KEY from https://poyo.ai\nPoYo.ai - Premium AI API Platform | Image, Video, Music & Chat APIs - 80% Cheaper\n","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":688,"installsAllTime":0,"installsCurrent":0,"stars":1,"versions":1},"createdAt":1773144184022,"updatedAt":1778997364037},"latestVersion":{"version":"1.0.0","createdAt":1773144184022,"changelog":"- Initial release of PoYo Grok Imagine Video skill.\n- Supports short text-to-video and image-to-video generation with motion controls via PoYo API.\n- Implements model selection, payload construction, and submission workflow.\n- Provides clear guidance on required parameters and output expectations.\n- Requires POYO_API_KEY and curl; see documentation for quickstart and examples.","license":"MIT-0"},"metadata":{"setup":[{"key":"POYO_API_KEY","required":true}],"os":null,"systems":null},"owner":{"handle":"coolhackboy","userId":"s177pant1v4gn5k13ffg1fp5b183nb02","displayName":"coolhackboy","image":"https://avatars.githubusercontent.com/u/13427145?v=4"},"moderation":null}