video-generation-minimax

Generate short videos from text prompts and image references via MiniMax APIs.

Updated Aug 27, 2026

Search Tags:#video generation #text-to-video #image-to-video #async polling #minimax api #subject reference

Ready to run

npx skills add https://github.com/eninem123/hunterclaw --skill video-generation-minimax

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: video-generation-minimax
Source: https://github.com/eninem123/hunterclaw/tree/main/skills/video-generation-minimax
Command: npx skills add https://github.com/eninem123/hunterclaw --skill video-generation-minimax

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

This Skill solves the problem of producing short videos from ideas and reference materials without manually editing footage by automating calls to MiniMax’s video generation APIs.

Core Features & Use Cases

Text-to-Video Generation: Turn a natural-language prompt into a generated video for quick ideation and storyboard drafts.
Image-to-Video & Start/End Frames: Create motion by using an initial image (or both first and last images) plus a prompt for scene continuity.
Subject Reference (Face Consistency): Generate videos based on a character/subject image and prompt to keep the subject’s features consistent.
Asynchronous Polling + Download: Automatically submit a generation task, poll task status, retrieve the resulting file, and save it to your workspace.
Use Case: Provide a prompt like “a woman in a coffee shop looking out the window” to generate a cinematic short clip for marketing or creative prototyping.

Quick Start

Use the skill to create a text-to-video by running: python3 {baseDir}/scripts/video_gen.py --mode text --prompt "镜头拍摄一个女性坐在咖啡馆里，女人抬头看着窗外".

Frequently Asked Questions about video-generation-minimax

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate a video from a text prompt using the MiniMax API?▼

To generate a video from a text prompt using the MiniMax API, submit a generation task with your natural-language prompt, poll the asynchronous status until completion, and download the resulting video file to your local workspace.

Can I use an image as a reference to generate a video?▼

Yes, you can generate videos using image-to-video, start and end frame, and subject reference modes to maintain scene continuity and character face consistency by providing an initial image alongside your text prompt.

Do I need an API key to run text-to-video generation tasks?▼

Yes, text-to-video generation tasks require a valid MINIMAX_API_KEY environment variable configured in your setup to authenticate and automate calls to MiniMax's video generation endpoints.

How does asynchronous polling work for video generation tasks?▼

Asynchronous polling for video generation works by automatically submitting a task to the API, continuously checking the task status until it returns Success or Fail, and then retrieving the completed output file.

What is subject reference mode for face consistency in video generation?▼

Subject reference mode is a video generation technique that uses a character or subject image alongside a prompt to keep the subject's facial features consistent throughout the generated video clip.

Are there limitations when using MiniMax API for image-to-video generation?▼

Image-to-video generation via the MiniMax API is designed for short videos and creative prototyping, requiring proper environment setup and asynchronous polling without guaranteeing immediate task completion.