together-video

What problem does it solve?

Generating engaging video content from text prompts and simple inputs can be slow and technically complex; this skill streamlines the process by coordinating model selection, framing, and optional references via Together AI's video API.

Core Features & Use Cases

• Text-to-Video: Create videos from descriptive prompts using a range of models (Veo, Sora, Kling, Seedance, etc.).
• Image-to-Video with Keyframes: Animate images with first/last frame control and reference images.
• Asynchronous Workflows: Submit jobs, poll for status, and download results; supports advanced parameters like width, height, seconds, fps, steps, and guidance_scale.
• Use Case: Marketing clips, tutorials, product demos, and social media content generation.

Quick Start

Run a basic test by generating a 1366x768 video from the prompt 'A serene sunset over the ocean'.