Open-Higgsfield

The open-source, multi-provider alternative to Higgsfield for AI image and video generation.

Generate with Freepik, Gemini, Google Vertex AI, and Vercel AI Gateway models from one focused creative studio.

Live Demo | Features | Providers | Quick Start | Contribute

Languages: 🇺🇸 English · 🇧🇷 Português · 🇪🇸 Español

AI media models are spread across providers, dashboards, payload formats, and incompatible controls. Open-Higgsfield brings them into one fast visual workspace:

• Generate images and videos in the same studio without switching products.
• Choose from 40 curated models across Freepik, Google AI Studio, Vertex AI, and Vercel AI Gateway.
• Use the right controls for every model with capability-driven aspect ratios, resolutions, duration, seed, CFG, safety, and audio options.
• Work with references naturally through image-to-image, image-to-video, start/end frames, video, and audio inputs.
• Switch providers without relearning the interface because tasks, progress, errors, and outputs use one consistent workflow.
• Bring your own API keys and own the stack with an MIT-licensed, self-hostable Next.js application.

Model discovery	Adaptive controls

The catalog includes Gemini Image, Veo, Flux, Recraft, GPT Image, Kling, Wan, Runway, Seedance, Seedream, PixVerse, LTX, MiniMax, Z-Image, and OmniHuman. Model availability, pricing, quotas, and preview access are controlled by each upstream provider.

See Providers and models for credentials, provider behavior, and extension instructions.

• Prompt-to-image and prompt-to-video generation
• Image-to-image and image-to-video workflows
• Start frame, end frame, character, motion, video, and audio references
• Model-aware aspect ratio, size, resolution, duration, seed, CFG, style, and safety controls
• Native audio and multi-shot options where supported
• Drag-and-drop, paste, upload, and public URL inputs
• Normalized synchronous and asynchronous generation tasks
• Live progress, reusable prompts, previews, and downloads
• Responsive desktop and mobile command interface
• Interface in English and Brazilian Portuguese
• Server-only provider credentials
• Local Node.js, Docker, and Vercel deployment support

• Next.js App Router and server route handlers
• React 19, strict TypeScript, Tailwind CSS 4, and Framer Motion
• Capability-driven model catalog and provider-neutral generation contracts
• Freepik API, Google Gen AI SDK, Vertex AI, and Vercel AI Gateway
• Cloudinary handoff for workflows that require public reference-media URLs
• PostgreSQL/Neon image history with a local filesystem fallback

flowchart LR
    U[Creative workspace] --> C[Model capabilities]
    C --> A[Generation API]
    A --> S[Provider-neutral service]
    S --> R[Provider registry]
    R --> F[Freepik]
    R --> G[Google AI Studio]
    R --> V[Vertex AI]
    R --> W[Vercel AI Gateway]
    F --> T[Normalized tasks and assets]
    G --> T
    V --> T
    W --> T
    T --> U

The UI reads model capabilities instead of provider-specific rules. The backend converts every request into canonical generation parameters, resolves the provider adapter, and normalizes synchronous results or asynchronous operations into the same task format.

See Architecture for the complete request lifecycle and extension points.

• Node.js 22+
• npm 10+
• At least one supported provider credential
• Cloudinary credentials only when a workflow requires public reference-media URLs

git clone https://github.com/TechBeme/open-higgsfield.git
cd open-higgsfield
npm install

cp .env.example .env.local

Configure only the providers you want to use:

# Freepik
FREEPIK_API_KEY=

# Google AI Studio
GEMINI_API_KEY=

# Google Vertex AI
GOOGLE_CLOUD_PROJECT=
GOOGLE_CLOUD_LOCATION=global
GOOGLE_SERVICE_ACCOUNT_JSON=

# Vercel AI Gateway
AI_GATEWAY_API_KEY=

# Reference-media uploads
CLOUDINARY_URL=

Never use NEXT_PUBLIC_ for provider credentials. Open-Higgsfield reads them only from server-side modules.

npm run dev

Open http://localhost:3000 and start generating.

cp .env.example .env.local
docker compose up --build

Docker stores generated files and task history in the open-higgsfield-data volume.

Use the Deploy with Vercel button at the top, then add credentials only for the providers you want enabled. Attach a custom domain after the first successful deployment.

Add DATABASE_URL to persist task history and generated images in PostgreSQL/Neon across Vercel cold starts and deployments. Temporary uploads, generated videos, and asynchronous workers still require durable object storage and queue infrastructure for full production resilience.

See Deployment for production and persistence guidance.

• Providers and models: credentials, supported integrations, and adding providers
• Architecture: capability system, provider registry, tasks, and storage
• Deployment: Vercel, Docker, Node.js, security, and persistence
• Contributing: development workflow and pull requests
• Security policy: responsible vulnerability reporting

Contributions are welcome, from new providers and model families to accessibility, translations, tests, and creative tooling.

1. Read CONTRIBUTING.md.
2. Fork the repository and create a focused branch.
3. Run npm run check.
4. Open a pull request using the provided template.

If Open-Higgsfield is useful to you, star the repository, share it with another creator, and show us what you build.

Do not report vulnerabilities in public issues. Follow SECURITY.md and never include provider credentials, private generated media, or personal data in reports.

Open-Higgsfield is an independent open-source project. It is not affiliated with, endorsed by, or sponsored by Higgsfield AI, Freepik, Google, Vercel, or any model provider. Product and model names belong to their respective owners. Availability, pricing, quotas, APIs, and capabilities may change upstream.

You are responsible for provider costs, generated content, deployment security, and compliance with provider terms and applicable law.

Released under the MIT License.