Available now

Photo Editing Toolkit: text removal

Photo Editing Toolkit is a set of 23 one-job photo edits, from aging a face and changing a background to removing text or restoring an old print.

Model ID

Input

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

The image containing text to be removed.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

Number of inference steps for sampling.

The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.

The same seed and the same prompt given to the same version of the model will output the same image every time.

Estimated total$0.07

You sign up first. Your settings are kept.

About this model

Overview

Each tool takes one photo and does one thing. Some need only the image: baby version, cartoon, color correction, face enhancement, photo restoration, professional photo, reframe, text removal. Others take a short phrase for what to change: age, background, expression, hair, objects to remove, scene, style, time of day, weather or thumbnail text.

A few style tools (broccoli haircut, plushie, realism, retouch, wojak, thumbnails) have a strength slider instead. Most tools let you pick the aspect ratio and save as JPEG or PNG.

What you can build

  • Fun portrait edits for social posts
  • Product and room photos with a new background or weather
  • Cleaned-up photos without text, clutter or color casts
  • Restored family photos and polished headshots
  • Video thumbnails from a single still

Prompting tips

  • Keep the phrase short and specific: "curly red shoulder-length hair" works better than a long description.
  • Use a photo where the face or subject is large and well lit; most tools change only part of it.
  • Lower the strength slider on the style tools if the result drifts too far from the person.

What to check

Compare facial proportions and identity. Generated aging is not a prediction of a person’s future appearance.

Inputs

  • Image (required): URL of the image containing text to be removed.
  • Guidance Scale (optional): The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. From 0 to 20.
  • Number of Inference Steps (optional): Number of inference steps for sampling. From 1 to 50.
  • Safety Tolerance (optional): The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive. Options: 1, 2, 3, 4, 5, 6.
  • Output Format (optional): The format of the generated image. Options: jpeg, png.
  • Aspect Ratio (optional): The aspect ratio of the generated image. Options: 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21.
  • Seed (optional): The same seed and the same prompt given to the same version of the model will output the same image every time.

Output and limits

  • Aspect ratios: 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21.
  • File formats: JPEG, PNG.
  • 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

  • 1 image: $0.07 / image