ArchestackBest of Open-Source AI: List on GitHub ↗ (opens in a new tab)

#5353rd of 79 in Image and videoFor image, video and design, image and design

open-higgsfield

Next.js studio for generating images and video with 38 hosted models

Live demo ↗ (opens in a new tab)Website ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
4.3k
License
no license
Last commit
Sep 2026
Language
TypeScript

Missed the latest GitHub check; these facts may be older.

Overview

A Next.js 16 web studio with one prompt bar that drives 8 image and 30 video models (Soul, Seedance, Kling, Wan, Flux and others) through a remote generation API. Server actions call that API with your own platform key, and results go into a gallery with reuse, favorites, bulk download and undo. History is kept in browser IndexedDB, and uploads go to Vercel Blob.

Who it is for: Creators wanting a self-hosted front-end for hosted image/video APIs

Strengths

  • Catalog-driven: a new model entry brings its own settings and media roles without studio changes
  • Gallery reuse restores model, settings and prompt, so runs can be re-rendered
  • Batch up to 4 results per press, with polling every 4s and a 10-minute deadline
  • Hosted version available, so no install is needed to try it

Weaknesses

  • No local inference: every generation goes to an external API and needs a platform key
  • Needs a Vercel Blob token for uploads and a generation API origin to self-host
  • No license file detected, so reuse terms are unclear
  • History is stored only in one browser, capped at 60 records, and old result URLs can expire

What it needs

  • no GPU
  • Needs Generation API (HF_API_BASE_URL) and platform key, Vercel Blob, Node.js and pnpm
  • Models: Soul 2, Seedance, Kling 3, Wan, Flux
  • port 3000

Also in Image and video

See all 79
Also in Image and video
RankProjectScore
1frigateLocal NVR with realtime object detection for IP cameras37.4k stars+923 (+2.5%) in 30 daysMIT93 out of 100
2MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles142.8k starsMIT88 out of 100
3toonflow-appInfinite-canvas tool for AI short drama and comic video production21.5k starsMIT87 out of 100
#4ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows146.5k starsGPL-3.086 out of 100
#5InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows29.1k starsApache-2.086 out of 100