Explore what you can build with the Phota API — editing, generation, and enhancement with identity preservation
The Phota API provides three core capabilities. Each one can optionally leverage trained profiles to
preserve the identity of specific people in the output.
The /edit endpoint takes one or more input images and a text prompt, then produces a transformed version. When you
reference a profile, the person’s identity is preserved even through dramatic transformations.
Before
After
”Make [[abc123]] look at the camera and create a portrait shot.”
Before
After
”Combine [[abc123]] from the first image and [[def456]] from the second image in one group shot.”
Before
After
”Convert to a solo portrait of [[abc123]].”
When to use it: adding or removing people from group shots, adjusting camera angle or lighting, restyling scenes
and backgrounds, creating seasonal or themed variations - anything where the edit needs to look like the real person.How profiles help: pass the user’s profile IDs in profile_ids so the API knows which identities to preserve. The
API matches the people in the input photo to the provided profiles automatically. You can also use [[profile_id]] in
the prompt to reference a specific person explicitly, e.g. "Make [[abc123]] smile wider".Example request body:
{ "prompt": "Make [[abc123]] smile wider", "images": ["https://example.com/photo.jpg"], "profile_ids": ["abc123"], # Optional, since profile_ids is mentioned in the prompt "aspect_ratio": "1:1", "resolution": "4K", "num_output_images": 2}
You can control the output aspect ratio (e.g. "9:16") and resolution (up to "4K") on every request. See Best practices.
The /generate endpoint creates images from a text prompt alone — no input image is needed. When you reference a
profile, the generated person looks exactly like the actual person (or pet).
Phota
”Artistic Noir Studio Headshot of [[abc123]], chest up. Introspective expression, gaze directed slightly off-camera, subtle three-quarter head tilt.”
Phota
”Playful, photorealistic portrait of [[abc123]] and [[def456]], emerging through torn festive paper. Their hands emerge through the torn paper, holding the edges as if the subjects are emerging from the paper.”
Phota
”Professional corporate headshot of [[abc123]]. Off-center to the right, smiling at camera, confident expression.”
When to use it: professional headshots, holiday cards and family portraits, profile pictures in any setting or style,
couple and group photos where everyone doesn’t need to be in the same room — any scenario where you need a photo-realistic image of specific people.How profiles help: the generated person matches the trained profile’s appearance — face shape, features, hair, and
skin tone are all preserved. Reference profiles directly in the prompt with [[profile_id]] syntax.Example request body:
{ "prompt": "A professional headshot of [[abc123]] in a modern office", "num_output_images": 4}
Generation is non-deterministic — set num_output_images to 2–4 and let the user pick the best result.
The /generate endpoint does not accept images or profile_ids. Reference profiles in the prompt with
[[profile_id]] syntax instead. If you need to transform an existing photo, use /edit.
The /enhance endpoint improves a photo automatically — no text prompt, no parameters to tune. Unlike most AI image
services, Phota infers all enhancement parameters on its own: lighting, sharpness, color balance, and overall quality.
Before
After
Before
After
Before
After
When to use it: photos taken in poor lighting, blurry or noisy images, photos with compression artifacts — any photo where quality fell short.How profiles help: when profile IDs are provided, enhancement preserves and can improve the rendering of known faces
in the photo.Example request body:
Before
After
Before
After
Before
After
Phota
Phota
Phota
Before
After
Before
After
Before
After