Available now

Phota: text to image

Phota creates photos from a written description and edits the images you upload, at 1K or 4K, on a choice of base models.

Model ID

Input

Fields marked * are required. Review the price before generating.

Text description of the desired image.

Example prompt. Edit it or write your own.

Additional settings
Estimated total · 1K$0.15

You sign up first. Your settings are kept.

About this model

Overview

Phota makes one to four images per run in five aspect ratios or an automatic shape, as JPEG or PNG. You pick the base model that draws the image; 4K works only with the default base model.

The edit mode takes up to 10 images and a written instruction.

What you can build

  • Portraits and lifestyle photos from a description
  • Edits that place a person or product into a new scene
  • The same prompt rendered by different base models to compare
  • 4K photos for print

Prompting tips

  • Write the prompt like a shot list: who, where, what light, which lens.
  • Try the same prompt on two base models before choosing one for a series.
  • Switch to 4K only on the default base model; the others render at 1K.

What to check

Compare facial structure, hair and clothing with any supplied reference.

Inputs

  • Prompt (required): Text description of the desired image.
  • Number of Images (optional): Number of images to generate. From 1 to 4.
  • Output Format (optional): The format of the generated image. Options: jpeg, png.
  • Resolution (optional): Resolution of the generated image. Options: 1K, 4K.
  • Aspect Ratio (optional): Aspect ratio of the generated image. Options: auto, 1:1, 16:9, 4:3, 3:4, 9:16.
  • Base Model (optional): Base model used to render the image. Identity composes on top of whichever base model is selected, so trained profiles work with all of them. Only `nb2` supports `4K`. Options: nb2, qwen-image-2, flux-2, seedream-5-pro.

Output and limits

  • Resolutions: 1K, 4K.
  • Aspect ratios: auto, 1:1, 16:9, 4:3, 3:4, 9:16.
  • File formats: JPEG, PNG.
  • Up to 4 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1K: $0.15 / image
  • 4K: $0.29 / image