Introducing Headshot AI, an open-source project from Leap AI that generates Professional AI Headshots in minutes.

The app is powered by:

• 🚀 Leap AI for AI model training
• 🚀 Leap AI to generate headshots
• ▲ Next.js for app and landing page
• 🔋 Supabase for DB & Auth
• 📩 Resend to email user when headshots are ready
• ⭐️ Shadcn with Tailwind CSS for styles
• 🔥 Replit for 1-click app run in the browser

Just add Stripe and you have a Headshot AI SaaS in a box.

To create your own Headshot AI app, follow these steps:

1. Clone the repository:

git clone https://github.com/leap-ai/headshots-starter.git

2. Enter the headshots-starter directory:

cd headshots-starter

3. Install dependencies:

   For npm:

   npm install

   For yarn:

   yarn

4. Create a new Supabase project and create the tables required for the app:

   • Rename .env.local.example to .env.local and update the values for NEXT_PUBLIC_SUPABASE_URL and NEXT_PUBLIC_SUPABASE_ANON_KEY from your Supabase project's API settings

   For this starter repo we disabled Row level permissions, you can enable them as needed for your own security, in the supasbase table settings

   

   This code block defines the schema for three tables: images, models, and samples.

   For any table column with foreign_key, make sure to link it while creating the column in Supabase.

   [images]

   • id (int8)
   • modelId (int8) (foreign_key)*
   • uri (text)
   • created_at (timestamptz)

   [models] - (Make sure to enable realtime on this table)

   • id (int8)
   • name (text)
   • type (text)
   • created_at (timestamptz)
   • user_id (uuid) (foreign_key)*
   • status (text)
   • modelId (text)

   [samples]

   • id (int8)
   • uri (text)
   • modelId (int8) (foreign_key)*

5. Create a Leap AI account

   In your .env.local file:

   • Fill in your_api_key with your Leap API key
   • Fill in your-hosted-url/leap/train-webhook with https://{your-hosted-url}/leap/train-webhook
   • Fill in your-hosted-url/leap/image-webhook with https://{your-hosted-url}/leap/image-webhook
   • Fill in your-webhook-secret with any arbitrary URL friendly string eg.shadf892yr398hq23h

   Note - on your first deploy you can use https://headshots-starter.vercel.app as a placeholder for your-hosted-url. Once you deploy your own app, swap the url in.

6. Create a Resend account

   • Fill in your-resend-api-key with your Resend API Key

7. Start the development server:

   For npm:

   npm run dev

   For yarn:

   yarn dev

8. Visit http://localhost:3000 in your browser to see the running app.

Deploy the example using Vercel:

Or fork the repo and Deploy using Replit.

The image samples used to teach the model what your face looks like are critical. Garbage in = garbage out.

• Enforce close-ups of faces and consider cropping so that the face is centered.
• Enforce images with only one person in the frame.
• Avoid accessories in samples like sunglasses and hats.
• Ensure the face is clearly visible. (For face detection, consider using tools like Cloudinary API).

If you get distorted results with multiple faces, repeated subjects, multiple limbs, etc, make sure to follow these steps and minimize the chance of this happening:

• Make sure any samples uploaded are the same 1:1 height / width aspect ratio, for example 512x512, 1024x1024, etc.
• Avoid mutiple people in the samples uploaded.
• Add "double torso, totem pole" to the negative prompt when generating.
• Make sure your dimensions when generating are also 1:1 with the same height / width ratios of the samples.

For more information on how to improve quality, read the blog here.

Headshot AI can be easily adapted to support many other use-cases on Leap AI including:

• AI Avatars
  • Anime
  • Portraits
  • Story Illustrations

• Pet Portraits

• Product Shots
• Food Photography

• Icons
• Style-Consistent Assets

& more!

We welcome collaboration and appreciate your contribution to Headshot AI. If you have suggestions for improvement or significant changes in mind, feel free to open an issue!

• Discord Community: Leap Discord
• Help Email: [email protected]

Headshot AI is released under the MIT License.