letorig/video-generator-client

Async Python wrapper for Seedance, Kling, MiniMax and Wan video generation. Supports CLI and a local web UI

What it solves

It provides a single, unified asynchronous Python client to interact with multiple different video-generation AI providers, eliminating the need to write separate integration code for each service.

How it works

The project acts as a wrapper around the APIs of providers like Seedance, Kling, MiniMax/Hailuo, and Wan. It offers a consistent interface via a Python SDK, a command-line interface (CLI), and a built-in web UI powered by FastAPI that allows users to trigger generations and poll for task status without needing a separate frontend build process.

Who it’s for

Developers and creators who want to generate AI videos using various high-end models (such as those from Alibaba, ByteDance, and Kuaishou) through a single tool rather than managing multiple disparate APIs.

Highlights

  • Multi-Provider Support: Integrates Seedance, Kling, MiniMax/Hailuo, and Wan.
  • Flexible Input: Supports both text-to-video and image-to-video workflows.
  • Built-in Web UI: Includes a FastAPI-based interface for model selection, prompt entry, and video preview/download with no Node.js requirement.
  • Comprehensive CLI: Allows for quick generation, provider discovery, and status checking directly from the terminal.

Related

  • Project
    madebyollin/taehv

    TAEHV is a tiny auto‑encoder that speeds up and memory‑optimizes video VAE decoding for many diffusion models (Hunyuan, MiniMax‑H3, Wan‑Video, CogVideoX, Open‑Sora, LTX‑2, etc.). It reduces decoding of a 61‑frame 512×320 clip from ~2‑3 s / 6‑9 GB to ~0.5 s / <0.5 GB, with a small quality trade‑off. The repo ships model checkpoints, Python API (`TAEHV`, `StreamingTAEHV`), example notebooks, and integration notes for ComfyUI, stable‑diffusion.cpp, SDNext, and Diffusers.

  • Project
    sb2702/free-ai-video-upscaler

    A free, browser-based AI video upscaler that allows users to increase video resolution without sign-ups or software downloads.

  • Project
    mira-wm/mira

    MIRA is a real-time world model of Rocket League that uses a 5B parameter latent diffusion model to simulate 2v2 matches based on player actions.

  • Project
    linzzzzzz/openclip

    An automated AI pipeline that extracts engaging highlights from long videos and livestreams, providing transcription, AI analysis, and automatic clip generation with subtitles and covers.