Skip to content

letorig /video-generator-client

Puts Seedance, Kling, MiniMax and Wan video models behind one Python tool
Model toolingMITEnglish README
Stars
551
30 days
New
Last push
4 days ago

About video-generator-client

Video Gen Client gives you Seedance, Kling, MiniMax and Wan behind one Python interface. You can run jobs from the command line or a local web UI. The web UI ships inside the package, so Node.js isn't needed. Each provider still needs its own paid API key in a `.env` file.

Best for: Python developers who want one interface to try Seedance, Kling, MiniMax and Wan.

What it does

  • Runs Seedance, Kling, MiniMax and Wan models through one Python client
  • Submits text-to-video and image-to-video jobs from the command line
  • Lists providers and models with video-gen providers and video-gen models
  • Serves a local web UI with no Node.js or frontend build step
  • Sets negative prompt, duration, aspect ratio and resolution in the UI
  • Polls task status, previews the video and downloads the MP4

Quickstart

Rewritten from the README. Check the repo for the latest steps.

  1. 1
    Clone the repo and enter it: the command below then cd video-generator-client
    git clone https://github.com/letorig/video-generator-client
  2. 2
    Make a virtual environment: python -m venv .venv then activate it (source .venv/bin/activate, or .venv\Scripts\activate on Windows)
  3. 3
    Install with the web extras: pip install -e ".[web]"
  4. 4
    Copy .env.example to .env and add credentials for the providers you use
  5. 5
    Run a job: the command below
    video-gen generate wan --prompt "A snowy forest at dawn" --model 2.1 --duration 5
  6. 6
    Start the local web UI: video-gen serve

Models and languages

Models it works with

  • Seedance 2.5
  • Seedance 2.0
  • Kling 3.0
  • Kling 2.6
  • Kling 2.5 Turbo
  • MiniMax H3
  • MiniMax Hailuo 2.3
  • Wan 3.0
  • Wan 2.7
  • Wan 2.6

Interface and docs

  • English

Alternatives

Other model tooling projects people compare with video-generator-client.

wide-trace

open-higgsfield

Self-hosted studio for 38 image and video models

Model tooling
  • Seedance 2.5
  • Seedance 2.0
  • Kling 3
  • +7
3.9k GitHub stars14 days agoNo license

MiniMax-AI

cli

MiniMax images, video, speech and text from your terminal

Model tooling
  • MiniMax H3
  • Hailuo-2.3
  • MiniMax-M3
  • +1
2.2k GitHub stars2 days agoNo license

higgsfield-ai

cli

40+ Higgsfield image, video, 3D and audio models from your terminal

Model tooling
  • Nano Banana Pro
  • Nano Banana 2 Lite
  • Gemini Omni Flash
  • +7
621 GitHub stars12 days agoMIT

Wan-Video

Wan2.2

Open video models for text, image, speech and character animation

Model tooling
  • Wan 2.2-T2V-A14B
  • Wan 2.2-I2V-A14B
  • Wan 2.2-TI2V-5B
  • +5
18k GitHub stars10 days agoApache-2.0

Featured on OpenMicroDrama

Do you maintain video-generator-client? Add this badge to your README so English speakers can find our write-up.

Featured on OpenMicroDrama
markdown
[![Featured on OpenMicroDrama](https://openmicrodrama.com/badges/featured.svg)](https://openmicrodrama.com/projects/letorig-video-generator-client)

The badge links to this page. Want your description changed? Email support@openmicrodrama.com.

Reviewed Oct 1, 2026. We write these descriptions ourselves. The repo's own docs are the final word.