agnes-free-video

Agnes Free Video

Use this skill to create and poll asynchronous video generation tasks with agnes-video-v2.0.

Credential Rule

Read the API key from the environment. Do not hardcode keys in prompts, scripts, skill files, commits, or shell history.

Preferred variable:

export AGNES_API_KEY="..."

The helper also accepts AGNES_TOKEN as a fallback.

Quick Start

Text-to-video:

python3 scripts/agnes_video.py create \
  --prompt "A cinematic shot of a cat walking on the beach at sunset, soft ocean waves, warm golden lighting, realistic motion" \

Image-to-video:

Keyframe transition:

Check an existing task:

Validate request shape without calling the API:

Workflow

1. Decide the mode: text-to-video, image-to-video, multi-image, or keyframe animation.
2. Write the prompt with subject, action, scene, camera movement, lighting, and style.
3. Keep num_frames at 81, 121, 161, 241, or 441 unless the user has a specific duration need.
4. Use scripts/agnes_video.py create to submit and poll. Use status if the user already has a task ID.
5. Download the video_url promptly when it appears.

Notes

• Create endpoint: POST https://apihub.agnes-ai.com/v1/videos
• Status endpoint: GET https://apihub.agnes-ai.com/v1/videos/{task_id}
• Model: agnes-video-v2.0
• Video generation is asynchronous.
• num_frames must be <= 441 and satisfy 8n + 1.
• Default helper settings are 1152x768, 121 frames, and 24 FPS.

Reference

Read references/api.md when you need request fields, task status values, error codes, or mode-specific prompt examples.