wide-trace/open-higgsfield

A studio for image and video generation — one prompt bar, each model’s own settings, and every finished run in one gallery.

What it solves

OpenHiggsfield AI is an open-source studio for generating images and videos. It removes the need for closed ecosystems and expensive studio subscriptions by allowing users to bring their own API keys to access a wide variety of generative models.

How it works

The application is built as a Next.js 16 app that acts as a frontend for various generation APIs. It uses a central catalog as the source of truth to dynamically render settings and media roles for each model. Users provide their own platform key, which is stored in an httpOnly cookie. Media uploads are handled via Vercel Blob for public URL generation, and generation history is persisted locally in the browser's IndexedDB.

Who it’s for

It is designed for creators and developers who work in long sessions, iterating on prompts, inputs, and settings across multiple different AI models without being locked into a single vendor.

Highlights

  • Multi-model support: Access to 38 models, including Soul 2, Kling 3, Flux, and others, from a single prompt bar.
  • Dynamic settings: Each model defines its own specific settings (aspect ratio, resolution, duration) which the studio renders automatically.
  • Unified composer: A single interface for both image and video generation.
  • Integrated gallery: A masonry grid with bulk actions, favorites, and a the ability to reuse previous runs to restore prompts and settings.
  • Self-hosted: Fully open-source and can be cloned and run locally.

Related

  • Project
    Anil-matcha/Open-Generative-AI

    An open-source, unrestricted AI media studio for generating images, videos, and audio using over 400 models with support for both cloud and local inference.

  • Project
    higgsfield-ai/cli

    A cross‑platform command‑line interface for Higgsfield’s suite of generative AI models (image, video, 3D, audio) plus utilities for building React web apps, publishing browser games, and managing personal “Soul” avatars—all from the terminal.

  • Dispatch
    Higgsfield AI Video Platform Integration with OpenAI Models

    Higgsfield is a generative media platform that uses GPT-4.1, GPT-5, and Sora 2 to transform product links and simple ideas into cinematic, social-first short-form videos.

  • Project
    SegFault42/HeliosGen

    HeliosGen is an open‑source desktop app (macOS released, Windows/Linux pending) that provides a visual, node‑based canvas for building and running AI image and video generation pipelines. It works locally, sending requests to the kie.ai API (or optionally a Codex CLI) and stores all data on the user’s machine. Features include multi‑model support, reference images, parallel/sequential execution, and a real‑time history. The app is built with Tauri 2 (Rust) and a Next.js/React front‑end, uses SQLite for local persistence, and is MIT‑licensed.

  • Project
    Anil-matcha/Open-AI-UGC

    Open AI UGC is an open‑source, self‑hostable web app that lets users generate short vertical UGC video ads using multiple state‑of‑the‑art text‑to‑video models. It includes Google OAuth, a credit system with Stripe billing, async webhook handling for renders, and a dashboard of past creations. The stack is Next.js 16, React 19, Tailwind, Prisma, and Muapi.ai for the underlying video generation.