ideogram/custom-models
Custom Models by Ideogram - advanced AI model for training. Delivers high-quality results with fast inference, suitable for both creative and production workflows.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runideogram/custom-modelsInput Schema
1 parameters · 0 required · 1 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
images_data_url | string | Optional | URL of a ZIP archive of training images. The archive must contain between 10 and 100 images (JPEG, PNG, or WebP). You may include caption sidecar files (``<stem>.txt``) to guide training -- captions are matched to images by filename stem. |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "ideogram/custom-models",
"prompt": "a beautiful sunset over mountains"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Ideogram
Ideogram Custom Models trains a private image model from a curated collection of ten to one hundred JPEG, PNG, or WebP examples. The training archive defines the recurring subject, visual identity, product language, or house style that future generations should learn, while optional caption sidecars associate precise written descriptions with individual images.
The workflow is designed for creative systems that need repeatability beyond prompt engineering alone: a compact but consistent dataset can establish a character, branded aesthetic, merchandise family, or specialized visual domain. Careful image selection and filename-matched captions give the training process cleaner evidence, helping the resulting model respond more reliably when it is later used for custom generation.
Highlights
Private visual training. Builds a reusable custom image model from an organization’s own curated examples.
Ten-to-one-hundred-image datasets. Accepts a practical training range that supports focused identities and styles without an enormous corpus.
Caption-aware learning. Optional filename-matched text sidecars clarify subjects, attributes, and visual concepts represented by each image.
Repeatable creative identity. Encodes a recurring character, product language, or brand aesthetic for later custom-model generations.
Pricing
| Billing unit | Price |
|---|---|
| Per request | $40 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The model's named workflow matches the source material and intended output | A different input modality or model route is required |
| A managed asynchronous result is suitable for the production pipeline | A synchronous, interactive editor is essential |
| The documented controls cover the required duration, framing, or format | The project needs controls outside this endpoint's schema |
| Creative iteration benefits from a repeatable request structure | Exact deterministic pixels, frames, geometry, or samples are mandatory |
| A finished downloadable media asset is the desired deliverable | Editable source layers or a native project file are required |
Prompt Guide
For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.
{}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | ideogram/custom-models |
| Inputs | images_data_url |
| Required inputs | None |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |