Skip to content
OpenMicroDrama

wide-trace /open-higgsfield

Self-hosted studio for 38 image and video models
Model toolingNo licenseEnglish README
Open on GitHubSave
Stars
3.9k
30 days
New
Last push
14 days ago

About open-higgsfield

OpenHiggsfield AI is a self-hosted web studio for images and videos. One prompt bar drives 38 models: 8 image and 30 video. You bring your own platform key, so there's no studio subscription. No license file ships with it, so reuse terms stay unclear.

Best for: Prompt tinkerers who want to self-host a studio and plug in their own platform key.

What it does

  • Drives image and video from one prompt bar; the model picks the output
  • Ships a searchable catalog of 38 models (8 image, 30 video)
  • Shows only the settings each model allows: ratio, resolution, duration, audio
  • Takes start frame, end frame, reference, video and audio inputs
  • Keeps a masonry gallery with favorites, reuse and bulk download
  • Restores model, settings and prompt when you reuse a run

Quickstart

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

  1. 1
    Install dependencies with pnpm install
  2. 2
    Start the dev server with pnpm dev and open http://localhost:3000
  3. 3
    Press **Add key** and paste your platform key as id:secret
  4. 4
    Set HF_API_BASE_URL and OPEN_HIGGSFIELD_READ_WRITE_TOKEN in your environment

Models and languages

Models it works with

  • Seedance 2.5
  • Seedance 2.0
  • Kling 3
  • Soul 2
  • Soul Cinema
  • Wan
  • Flux
  • Ideogram
  • Recraft
  • LTX

Interface and docs

  • English

Alternatives

Other model tooling projects people compare with open-higgsfield.

letorig

video-generator-client

Puts Seedance, Kling, MiniMax and Wan video models behind one Python tool

Model tooling
  • Seedance 2.5
  • Seedance 2.0
  • Kling 3.0
  • +7
551 GitHub stars4 days agoMIT

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

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

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 open-higgsfield? 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/wide-trace-open-higgsfield)

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

Reviewed Oct 1, 2026. Unofficial alternative to Higgsfield AI; not affiliated with Higgsfield. We write these descriptions ourselves. The repo's own docs are the final word.