Generate videos from text prompts via Together AI's video API.
npx skills add https://github.com/zainhas/togetherai-skills --skill together-video
Please help me install this Agent Skill. Skill: together-video Source: https://github.com/zainhas/togetherai-skills/tree/main/skills/together-video Command: npx skills add https://github.com/zainhas/togetherai-skills --skill together-video
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.
Run a basic test by generating a 1366x768 video from the prompt 'A serene sunset over the ocean'.
High-intent search queries and answers about installing and using this skill.
Generate video from text prompts using Together AI by submitting descriptive text to models like Veo, Sora, or Kling via API. You define width, height, seconds, fps, and guidance_scale parameters to produce the final video output asynchronously.
Yes, you can animate images using image-to-video workflows with keyframes. By providing first and last frame control alongside reference images through the Together AI API, you can direct the animation sequence and generate the final video.
Text-to-video generation requires model IDs, input prompts, and parameters such as width, height, seconds, fps, steps, guidance_scale, and seed. Optional reference images can also be included to guide the video output.
Asynchronous video generation works by submitting a job to the Together AI API, polling for status updates, and downloading the video result once processing completes. This allows long rendering tasks to run without blocking execution.
Supported AI video models include Veo, Sora, Kling, and Seedance. These models generate videos from prompts and are suitable for creating marketing clips, tutorials, product demos, and social media content.
Reference images are optional inputs used to guide video generation workflows. The metadata does not specify strict limitations on reference images, but results depend on the selected model's capabilities and the provided prompt parameters.
AceDataCloudGenerate AI videos from text prompts, reference images, or existing video IDs.
wanyusheng63-altGenerate videos from text prompts or images via the Tencent Cloud Hunyuan Video API.
zai-orgGenerate detailed text prompts from images and videos for AI synthesis.
marcosbatallas99Generate marketing videos with AI models, avatars, and programmatic frameworks.
