Image
Ideogram Custom Models
Generate images with a trained Ideogram custom model.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Ideogram Custom Models. Review your own result before publishing.
A starting point.
Use a completed custom model when a learned subject or visual identity should guide new scenes.
Before you publish.
Check whether the learned subject survives changes in viewpoint and lighting.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Supply model_id and prompt. model_id must identify a model whose training has completed.
Select aspect_ratio and begin with num_images 1. Compare rendering_speed and expand_prompt while preserving the same model and seed.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for ideogram/custom-models/generate. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
model_id | Text | Required | Min. characters: 1 |
prompt | Text | Required | Min. characters: 1 |
aspect_ratio | Text | Optional | 1:3, 3:1, 1:2, 2:1, 9:16, 16:9, 10:16, 16:10, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 1:1 |
expand_prompt | On/off | Optional | — |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 8 |
rendering_speed | Text | Optional | — |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Ideogram Custom Models through the API.
Start with this model ID for the endpoint featured on this page:
ideogram/custom-models/generate
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.