> ## Documentation Index
> Fetch the complete documentation index at: https://docs.slai.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Stable Diffusion API

> Building an API to generate images with stable diffusion

### Define the environment

First, create a file with your Beam App definition. You can name this whatever
you want. In this example, name it `app.py`.

```python app.py theme={null}
import beam

# The environment your code will run on
app = beam.App(
    name="stable-diffusion",
    cpu=4,
    memory="16Gi",
    gpu=1,
    python_version="python3.8",
    python_packages=["diffusers", "transformers", "torch", "pillow"],
)

# Deploys function as async webhook
app.Trigger.Webhook(
    inputs={"prompt": beam.Types.String()},
    outputs={},
    handler="run.py:generate_image"
)

# File to store image outputs
app.Output.File(path="output.png", name="myimage")

# Persistent volume to store cached model
app.Mount.PersistentVolume(app_path="./cached_models", name="cached_model")
```

### Inference Function

Write a simple function that takes a prompt passed from the user, and returns an image generated using Stable Diffusion.

<Warning>
  You need an access token from Huggingface to run this example. You can sign up
  for Huggingface and access your token on [the settings
  page](https://huggingface.co/settings/tokens), and store it in the [Beam
  Secrets Manager](/beam/account/secrets-management).
</Warning>

Notice the `image.save()` method below. You defined a file path called `output.png` in `app.py`, and that's where your images will be saved.

```python run.py theme={null}
import os

# Specify the HuggingFace model cache before the diffusers library is imported
os.environ["TRANSFORMERS_CACHE"] = "/workspace/cached_models"
os.environ["HF_HOME"] = "/workspace/cached_models"

import torch
from torch import autocast
from diffusers import StableDiffusionPipeline
from PIL import Image


def generate_image(**inputs):
    pipe = StableDiffusionPipeline.from_pretrained(
        "CompVis/stable-diffusion-v1-4",
        torch_dtype=torch.float16,
        revision="fp16",
        # Add your own access token from Huggingface
        use_auth_token=os.environ["HUGGINGFACE_API_KEY"],
    ).to("cuda")

    prompt = inputs["prompt"]

    with autocast("cuda"):
        image = pipe(prompt, guidance_scale=7.5).images[0]
        print(image)

    image.save("output.png")
```

### Deploying the API

In your teriminal, run:

```curl theme={null}
beam deploy app.py
```

You'll see the deployment appear in the dashboard.

<img src="https://mintcdn.com/slai-docs/0GTBstnyDK-8Z9OV/img/beam/getting-started/new-deployment.png?fit=max&auto=format&n=0GTBstnyDK-8Z9OV&q=85&s=5818022a032a606a76076a1400d21356" alt="Deployment" width="1196" height="488" data-path="img/beam/getting-started/new-deployment.png" />

### Generating images

In the dashboard, click **Call API** to view the API URL.

<img src="https://mintlify.s3.us-west-1.amazonaws.com/slai-docs/img/tools/call-api.png" alt="" />

Paste the code into your terminal to make a request.

```curl theme={null}
  curl -X POST --compressed "https://beam.slai.io/jrg5v" \
   -H 'Accept: */*' \
   -H 'Accept-Encoding: gzip, deflate' \
   -H 'Authorization: Basic [YOUR_AUTH_TOKEN]' \
   -H 'Connection: keep-alive' \
   -H 'Content-Type: application/json' \
   -d '{"prompt": "a renaissance style photo of steve jobs"}'
```

The API returns a Task ID.

```json theme={null}
{ "task_id": "edbcf7ff-e8ce-4199-8661-8e15ed880481" }
```

### Querying the status of a job

You will use the `/task` API to retrieve the status of a job, passing in the Task ID.

```curl theme={null}
curl -X POST --compressed "https://api.slai.io/beam/task" \
  -H 'Accept: */*' \
  -H 'Accept-Encoding: gzip, deflate' \
  -H 'Authorization: Basic [YOUR_AUTH_TOKEN]' \
  -H 'Content-Type: application/json' \
  -d '{
	"action": "retrieve",
	"task_id": "edbcf7ff-e8ce-4199-8661-8e15ed880481"
}'
```

This returns the generated image in the `outputs` dictionary, as a pre-signed URL.

```json theme={null}
{
  "outputs": {
    "myoutput": "https://beam-data.slai.io/beam.slai.io/z6sks/outputs/z6sks-0041/53b8338c-d905-4356-845d-a259ec279cab/myoutput.zip"
  },
  "started_at": "2022-11-04T19:43:25.668303Z",
  "ended_at": "2022-11-04T19:43:26.017401Z",
  "task_id": "edbcf7ff-e8ce-4199-8661-8e15ed880481"
}
```