Photoshot is an open-source AI avatar generator web application designed for users who want to create personalized avatars using AI. It leverages cloud-based machine learning models to transform user-uploaded photos into stylized avatars, offering a convenient and automated solution for digital self-representation.

How It Works

The application utilizes Next.js for its frontend framework and integrates with Replicate, a platform for running machine learning models. Specifically, it employs Flux, an open-source text-to-image generation model, and likely a Dreambooth model for personalized avatar training. User data and generated images are stored in AWS S3 buckets, with payments handled via Stripe.

Quick Start & Requirements

• Install dependencies: yarn install
• Run local database and maildev server: docker-compose up -d
• Configure .env.local with credentials for PostgreSQL, AWS S3, Replicate, Stripe, and email services.
• Run migrations: yarn prisma:migrate:dev
• Start development server: npm run dev or yarn dev
• Access at http://localhost:3000
• Requires Node.js, Yarn/npm, Docker, PostgreSQL, AWS S3 access, Replicate API token, and Stripe API key.

Highlighted Details

• AI avatar generation powered by Replicate and Flux models.
• Integrates Stripe for payment processing.
• Uses NextAuth.js for authentication.
• Supports AWS S3 for image storage.
• Includes an OpenAI-powered prompt wizard.

Maintenance & Community

No specific information on contributors, sponsorships, or community channels (like Discord/Slack) is provided in the README.

Licensing & Compatibility

The README does not explicitly state a license. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project requires significant external service configuration (AWS S3, Replicate, Stripe) and relies on cloud-hosted ML models, incurring potential costs and external dependencies. The setup involves managing multiple environment variables and database migrations.