PhotaYour Face. Any Scene. Always You.
Your Identity. Preserved Perfectly.
Photos That Look Like You
Train a personal profile from 30-50 photos. Phota learns your facial features, expressions, and angles, then generates new images that faithfully preserve who you are. No generic lookalikes, no identity drift.
Edit Scenes, Keep the Person
Describe changes in plain language and Phota executes them while maintaining identity fidelity. Swap backgrounds, adjust lighting, change outfits, or fix expressions. Accepts up to 10 input images per request.
Upscale Without Losing Detail
Enhance and upscale photos while preserving facial identity and fine details. Fix low-resolution images, sharpen features, and improve quality without altering who is in the picture.
Generate, edit, enhance, and train
Create personalized photos from text, edit existing images, enhance quality, or train a profile for identity-consistent generation.
See what Phota can create
Copy any prompt below and try it yourself in the playground.
"A professional headshot in a modern office with soft natural window light, wearing a navy blazer, confident smile, shallow depth of field"
"Standing on a rooftop at golden hour overlooking a city skyline, wind in hair, casual outfit, warm cinematic tones, shot on 35mm film"
"A candid photo at a bustling Italian cafe, espresso in hand, natural afternoon light, cobblestone street in the background, documentary style"
"A dramatic studio portrait with Rembrandt lighting, dark background, sharp focus on the face, wearing a black turtleneck, fine art photography style"
A few lines of code.
Photos that look like you.
fal.ai handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPUs to manage.
- Serverless: scales to zero, scales to millions
- Pay per image, no minimums
- Python and JavaScript SDKs, plus REST API
import fal_client
result = fal_client.subscribe(
"fal-ai/phota",
arguments={
"prompt": "A professional headshot, soft window light",
"aspect_ratio": "1:1",
}
)
# result["images"][0]["url"] → your generated imageCommon questions about Phota
What is Phota?
Phota is a personalized AI photo generation model by PhotaLabs, founded by former Adobe AI researchers. It separates identity from scene, allowing you to generate, edit, and enhance photos that faithfully preserve who you are across any style, setting, or composition.
How does the profile training work?
Upload 30-50 photos of a person via the Create Profile endpoint ($2.90/training). Phota trains a Subject Token that captures facial features, expressions, and angles. Reference this profile in any generation or editing prompt using the profile ID to maintain consistent identity.
Do I need a profile to use Phota?
No. Text-to-image, editing, and enhancement all work without a profile. The profile is optional for when you want identity-consistent results across multiple generations.
What resolutions are supported?
Phota generates at 1K (standard) and 4K resolution. Multiple aspect ratios are supported including 1:1, 16:9, 4:3, 3:4, and 9:16. Output formats include JPEG, PNG, and WebP.
How much does Phota cost on fal.ai?
Text-to-image and editing: $0.09/image at 1K, $0.18/image at 4K. Enhancement: $0.13/image. Profile training: $2.90 per training run. Pay-per-use with no minimums or subscriptions.
How do I get started with the API?
Install the fal.ai SDK (Python or JavaScript), grab an API key from your dashboard, and make your first request in a few lines of code. The API is serverless, so no GPUs to manage. Check the API documentation for all available parameters.
Can I use Phota for commercial projects?
Yes. Images generated through the fal.ai API can be used in commercial projects. Check fal.ai's terms of service for full details on usage rights and licensing.
Ready to create?
Start generating personalized AI photos with Phota on fal.ai.