> For the complete documentation index, see [llms.txt](https://netmind-power.gitbook.io/netmind-power-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://netmind-power.gitbook.io/netmind-power-documentation/api/inference/images.md).

# Images

## Overview

Netmind provides compatibility with the OpenAI API standard, allowing for easier integration into existing applications.

## Base URL

`https://api.netmind.ai/inference-api/openai/v1`

## API Key

To use the API, you need to obtain a Netmind AI API Key. For detailed instructions, please refer to the [authentication documentation](https://netmind-power.gitbook.io/netmind-power-documentation/api/api-token).

## Supported Models

### Image Generation

* runwayml/stable-diffusion-v1-5
* black-forest-labs/FLUX.1-schnell
* stabilityai/stable-diffusion-3.5-large

### Image Edit

* black-forest-labs/FLUX.1-Depth-dev
* black-forest-labs/FLUX.1-Canny-dev
* black-forest-labs/FLUX.1-Fill-dev

### Image Variation

* black-forest-labs/FLUX.1-Redux-dev

## Usage Examples

The Image API is compatible with the OpenAI Python SDK.Below is an example of how to use it.

### Image Generation

#### Python Client

```python
from openai import OpenAI
import base64
client = OpenAI(
    base_url="https://api.netmind.ai/inference-api/openai/v1",
    api_key="<YOUR API Key>",
)
response = client.images.generate(
    model="black-forest-labs/FLUX.1-schnell",
    prompt="Generate a cup of coffee",
    response_format="b64_json"
)
image_base64 = response.data[0].b64_json
with open("generated_image.png", "wb") as f:
    f.write(base64.b64decode(image_base64))
```

#### CURL Example

```sh
# Set your API key
export API_KEY="<YOUR API Key>"
curl -X POST "https://api.netmind.ai/inference-api/openai/v1/images/generations" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${API_KEY}" \
  -d '{
    "model": "stabilityai/stable-diffusion-3.5-large",
    "prompt": "Generate a cup of coffee",
    "response_format": "b64_json"
  }' -o response.json
  cat response.json| jq -r ".data[0].b64_json" | base64 --decode > generated_image.png

```

### Image Edit

The `black-forest-labs/FLUX.1-Depth-dev` and `black-forest-labs/FLUX.1-Canny-dev` models do not require a mask file for image editing, whereas the `black-forest-labs/FLUX.1-Fill-dev` model necessitates a mask file to perform image modifications.

#### Python Client

```python
from openai import OpenAI
import base64

client = OpenAI(
    base_url="https://api.netmind.ai/inference-api/openai/v1",
    api_key="<YOUR API Key>",
)

response = client.images.edit(
    model="black-forest-labs/FLUX.1-Fill-dev",
    image=open("image.png", "rb"),
    mask=open("mask.png", "rb"),
    prompt="Turn hair blue",
    response_format="b64_json",
)

image_base64 = response.data[0].b64_json
with open("generated_image.png", "wb") as f:
    f.write(base64.b64decode(image_base64))
```

#### CURL Example

```sh
# Set your API key
export API_KEY="<YOUR API Key>"
curl -X POST "https://api.netmind.ai/inference-api/openai/v1/images/edits" \
  -H "Authorization: Bearer ${API_KEY}" \
  --form 'model="black-forest-labs/FLUX.1-Fill-dev"' \
  --form 'prompt="Turn hair blue"' \
  --form 'response_format="b64_json"' \
  --form 'image=@"image.png"' \
  --form 'mask=@"mask.png"' -o response.json
 cat response.json| jq -r ".data[0].b64_json" | base64 --decode > generated_image.png
```

### Image Variation

#### Python Client

```python
from openai import OpenAI
import base64

client = OpenAI(
    base_url="https://api.netmind.ai/inference-api/openai/v1",
    api_key="<YOUR API Key>",
)

response = client.images.create_variation(
    model="black-forest-labs/FLUX.1-Redux-dev",
    image=open("image.png", "rb"),
    response_format="b64_json",
)

image_base64 = response.data[0].b64_json
with open("generated_image.png", "wb") as f:
    f.write(base64.b64decode(image_base64))
```

#### CURL Example

```sh
# Set your API key
export API_KEY="<YOUR API Key>"
curl -X POST "https://api.netmind.ai/inference-api/openai/v1/images/variations" \
  -H "Authorization: Bearer ${API_KEY}" \
  --form 'model="black-forest-labs/FLUX.1-Redux-dev"' \
  --form 'response_format="b64_json"' \
  --form 'image=@"image.png"' -o response.json
cat response.json| jq -r ".data[0].b64_json" | base64 --decode > generated_image.png
```

## Model Parameters

### Image Generation

* `model`: ID of the model to use. (required)
* `prompt`: A text description of the desired image(s). (required)
* `size`: Image size, format is width x height. (optional)
* `response_format`: The format in which the generated images are returned. Currently supports two options: b64\_json and url. If the url format is selected, please note that the URL will expire 24 hours after generation. Make sure to download the file before the expiration time. (optional)

### Image Edit

* `model`: ID of the model to use. (required)
* `prompt`: The prompt to use for image edit. (required)
* `response_format`: The format in which the generated images are returned. Currently supports two options: b64\_json and url. If the url format is selected, please note that the URL will expire 24 hours after generation. Make sure to download the file before the expiration time. (optional)
* `image`: The image to use for image edit. (required)
* `mask`: The mask to use for image edit. (optional)

### Image Variation

* `model`: ID of the model to use. (required)
* `image`: The image to use for image variation. (required)
* `response_format`: The format in which the generated images are returned. Currently supports two options: b64\_json and url. If the url format is selected, please note that the URL will expire 24 hours after generation. Make sure to download the file before the expiration time. (optional)