> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/openai/openai-python/llms.txt
> Use this file to discover all available pages before exploring further.

# Image Variations

Creates a variation of a given image.

This endpoint only supports `dall-e-2`.

## Method Signature

```python theme={null}
client.images.create_variation(
    image=open("image.png", "rb"),
    n=2,
    size="1024x1024"
)
```

## Parameters

<ParamField path="image" type="file" required>
  The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.
</ParamField>

<ParamField path="model" type="string">
  The model to use for image generation. Only `dall-e-2` is supported at this time.
</ParamField>

<ParamField path="n" type="integer">
  The number of images to generate. Must be between 1 and 10.
</ParamField>

<ParamField path="response_format" type="string">
  The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated.
</ParamField>

<ParamField path="size" type="string">
  The size of the generated images. Must be one of:

  * `256x256`
  * `512x512`
  * `1024x1024`
</ParamField>

<ParamField path="user" type="string">
  A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
</ParamField>

## Returns

Returns an `ImagesResponse` object containing the image variations.

<ResponseField name="created" type="integer">
  The Unix timestamp (in seconds) of when the image was created.
</ResponseField>

<ResponseField name="data" type="array">
  The list of generated images.

  <Expandable title="Image object">
    <ResponseField name="url" type="string">
      The URL of the generated image (when `response_format=url`). URLs are only valid for 60 minutes.
    </ResponseField>

    <ResponseField name="b64_json" type="string">
      The base64-encoded JSON of the generated image (when `response_format=b64_json`).
    </ResponseField>
  </Expandable>
</ResponseField>

## Examples

### Create variations with URL response

```python theme={null}
from openai import OpenAI
client = OpenAI()

response = client.images.create_variation(
    image=open("image.png", "rb"),
    n=3,
    size="1024x1024"
)

for i, image in enumerate(response.data):
    print(f"Variation {i + 1}: {image.url}")
```

### Create variations with base64 response

```python theme={null}
import base64
from openai import OpenAI

client = OpenAI()

response = client.images.create_variation(
    image=open("original.png", "rb"),
    n=2,
    size="512x512",
    response_format="b64_json"
)

for i, image in enumerate(response.data):
    image_data = base64.b64decode(image.b64_json)
    with open(f"variation_{i}.png", "wb") as f:
        f.write(image_data)
    print(f"Saved variation_{i}.png")
```

### Multiple smaller variations

```python theme={null}
from openai import OpenAI
client = OpenAI()

# Generate 10 small variations for quick preview
response = client.images.create_variation(
    image=open("source.png", "rb"),
    n=10,
    size="256x256"
)

print(f"Generated {len(response.data)} variations")
for i, image in enumerate(response.data):
    print(f"Variation {i + 1}: {image.url}")
```