ideogram/character/text-to-imageIdeogram Character, Ideogram's July 2025 consistency model, takes one portrait and a written scene and returns up to four new images that keep that face and hairstyle, in Turbo, Balanced or Quality.
Filtering differs by endpoint: Text to image — Uncensored, Image editing — Softened.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
Outputbalcony-slip-dress Turbo returned this 992 × 992 image in about 27 seconds; the fringe and the small mark above her lip carried over from the headshot.
- turbo
Outputvanity-red-lipstick One Balanced call with num_outputs 2 returned two 992 × 992 takes in about 54 seconds; this is the first.
- 1207
- realistic
- balanced
This example starts at $0.08 per image. The Playground updates the estimate when you change the settings.
