> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developer.ideogram.ai/v1/tutorials/custom-model-training/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developer.ideogram.ai/_mcp/server.

> Train a custom Ideogram model on your own images using datasets, then generate with your custom model URI.

# Custom Model Training

Train a custom model on your own images, then use it to generate new images in your unique style.

## Overview

Custom model training lets you fine-tune an Ideogram model on your own dataset of images. Once training completes, you can use the model with the **Generate** endpoint by passing its `custom_model_uri`.

The workflow has four steps:

1. **Create a dataset** to hold your training images.
2. **Upload images** (and optional captions) to the dataset.
3. **Start training** to kick off the model training job.
4. **Generate images** using your trained model.

## Step 1: Create a Dataset

#### Python

```python
import requests

response = requests.post(
  "https://api.ideogram.ai/datasets",
  headers={"Api-Key": "<apiKey>"},
  json={"name": "My Training Dataset"}
)
dataset = response.json()
dataset_id = dataset["dataset_id"]
print(f"Created dataset: {dataset_id}")
```

#### cURL

```bash
curl -X POST https://api.ideogram.ai/datasets \
  -H "Api-Key: <apiKey>" \
  -H "Content-Type: application/json" \
  -d '{"name": "My Training Dataset"}'
```

## Step 2: Upload Training Images

Upload your training images to the dataset. You can upload individual images (JPEG, PNG, WebP), optional `.txt` caption sidecar files, or ZIP archives containing both.

* A dataset needs **at least 10 images** to start training.
* A dataset can hold **up to 100 images**.
* Caption files are matched by filename stem (e.g. `sunset.txt` captions `sunset.jpg`).

#### Python

```python
import requests
import glob

# Upload individual images
files = [("files", open(f, "rb")) for f in glob.glob("training_images/*.jpg")]

response = requests.post(
  f"https://api.ideogram.ai/datasets/{dataset_id}/upload_assets",
  headers={"Api-Key": "<apiKey>"},
  files=files
)
result = response.json()
print(f"Uploaded {result['success_count']}/{result['total_count']} images")
```

#### cURL

```bash
curl -X POST https://api.ideogram.ai/datasets/<dataset_id>/upload_assets \
  -H "Api-Key: <apiKey>" \
  -H "Content-Type: multipart/form-data" \
  -F files=@image1.jpg \
  -F files=@image2.jpg \
  -F files=@image3.jpg
```

> **Info**
>
> You can also upload a ZIP file containing images and captions together, which is convenient for larger datasets.

## Step 3: Train the Model

Once your dataset has enough images, start training by giving your model a name.

#### Python

```python
import requests

response = requests.post(
  "https://api.ideogram.ai/v1/ideogram-v3/train-model",
  headers={"Api-Key": "<apiKey>"},
  json={"dataset_id": dataset_id, "model_name": "my-custom-model"}
)
training = response.json()
model_id = training["model_id"]
print(f"Training started: {training['training_status']}")
```

#### cURL

```bash
curl -X POST https://api.ideogram.ai/v1/ideogram-v3/train-model \
  -H "Api-Key: <apiKey>" \
  -H "Content-Type: application/json" \
  -d '{"dataset_id": "<dataset_id>", "model_name": "my-custom-model"}'
```

## Checking Training Status

Poll the model details endpoint to check when training completes.

#### Python

```python
import requests
import time

while True:
  response = requests.get(
    f"https://api.ideogram.ai/models/{model_id}",
    headers={"Api-Key": "<apiKey>"}
  )
  model = response.json()["model"]
  print(f"Status: {model['status']}")

  if model["status"] == "COMPLETED":
    print(f"Model ready! URI: {model.get('custom_model_uri')}")
    break
  elif model["status"] == "ERRORED":
    print("Training failed.")
    break

  time.sleep(60)
```

#### cURL

```bash
curl -X GET https://api.ideogram.ai/models/<model_id> \
  -H "Api-Key: <apiKey>"
```

## Step 4: Generate with Your Model

Once training is complete and `is_available_for_generation` is `true`, use the `custom_model_uri` from the model details to generate images.

#### Python

```python
import requests

response = requests.post(
  "https://api.ideogram.ai/v1/ideogram-v3/generate",
  headers={"Api-Key": "<apiKey>"},
  files={
    "prompt": (None, "A photo in my custom style"),
    "custom_model_uri": (None, "model/my-custom-model/version/1"),
    "rendering_speed": (None, "DEFAULT")
  }
)
result = response.json()
if response.status_code == 200:
  print(result["data"][0]["url"])
```

#### cURL

```bash
curl -X POST https://api.ideogram.ai/v1/ideogram-v3/generate \
  -H "Api-Key: <apiKey>" \
  -H "Content-Type: multipart/form-data" \
  -F prompt="A photo in my custom style" \
  -F custom_model_uri="model/my-custom-model/version/1" \
  -F rendering_speed="DEFAULT"
```

## Tips for Better Results

* **Use high-quality images** that clearly represent the style or subject you want the model to learn.
* **Add captions** to guide the model on what each image represents. Captions are optional!
* **Use consistent subjects** across your training images for best results with style transfer.

> Train a custom Ideogram model on your own images using datasets, then generate with your custom model URI.