skillfed

byted-seedance-video-generate

This skill leverages Seedance 1.0/1.5 models to generate videos from text descriptions, with optional guidance from images, videos, and audio. You can control output parameters like aspect ratio, duration, resolution, and frame count, and optionally generate accompanying audio. Supports multiple input modes including text-only, frame-guided, and multimodal reference workflows.

Byted-seedance-video-generate creates videos from text prompts using Seedance AI models with support for frame and reference guidance.

AI-generated summary based on this skill's SKILL.md

378 84 Apache-2.0 updated by bytedance

Install

bytedance/agentkit-samples/byted-seedance-video-generate · repository language: Python

CLI (skillfed)coming soon
git clone https://github.com/bytedance/agentkit-samples
cp -r agentkit-samples/skills/byted-seedance-video-generate ~/.claude/skills/byted-seedance-video-generate

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I generate video from text prompt using byted-seedance-video-generate?

byted-seedance-video-generate leverages Seedance 1.0/1.5 models to create videos directly from text descriptions. You provide a text prompt describing your desired video content, and the skill generates a video matching that description. You can control output parameters including aspect ratio, duration, resolution, and frame count to customize the result to your needs.

Can byted-seedance-video-generate create video with images as guidance?

Yes, byted-seedance-video-generate supports image-guided video generation. You can provide reference images such as first or last frames to guide the video creation process, or use other reference images to influence the output style and content. This frame-guided mode gives you more control over the final video's appearance and direction.

What multimodal inputs does byted-seedance-video-generate accept?

byted-seedance-video-generate accepts multiple input modes including text descriptions, images, videos, and audio. This multimodal capability lets you combine different reference materials—such as using an image for visual guidance alongside a text prompt, or incorporating audio synthesis—to create more precisely controlled video outputs.

Does byted-seedance-video-generate support batch video generation?

Yes, byted-seedance-video-generate can batch process multiple video generation requests. This allows you to generate several videos in a single operation, making it efficient for workflows requiring multiple video outputs at once.

Can byted-seedance-video-generate generate video with audio?

byted-seedance-video-generate includes audio synthesis capability, allowing you to generate accompanying audio alongside your videos. This multimodal feature enables you to create complete video content with synchronized audio output in a single generation pass.

What parameters can I control in byted-seedance-video-generate?

byted-seedance-video-generate lets you control multiple output parameters including aspect ratio, duration, resolution, and frame count. These customizable settings give you flexibility to generate videos optimized for different platforms, use cases, and quality requirements.

SKILL.md

rendered from the published skill — quoted content, verbatim

Video Generate Skill

This skill generates videos using Doubao Seedance 1.0/1.5 models.

Trigger Conditions

  1. User wants to generate videos from text descriptions
  2. User wants to create videos based on images (first/last frame)
  3. User wants to create videos with reference materials (images, videos, audio)
  4. User asks for video generation capabilities

Usage

Environment Variables

Before using this skill, ensure the following environment variables are set:

  • ARK_API_KEY or MODEL_VIDEO_API_KEY or MODEL_AGENT_API_KEY: API key for the video generation service
  • MODEL_VIDEO_API_BASE: API base URL (optional, has default)
  • MODEL_VIDEO_NAME: Model name (optional, has default)
Function Signature
async def video_generate(
    params: list,
    batch_size: int = 10,
    max_wait_seconds: int = 1200,
    model_name: str = None,
) -> Dict:
Parameters
params (list[dict])

A list of video generation requests. Each item is a dict with

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 3 files
skills/byted-seedance-video-generate/LICENSE.txt
skills/byted-seedance-video-generate/SKILL.md
skills/byted-seedance-video-generate/scripts/video_generate.py

Related skills

Tags

text-to-video multimodal-generation frame-guidance video-synthesis reference-based batch-processing audio-generation aspect-ratio-control seedance-models transition-animation