image generation

Playground V2 Aesthetic

A text to image model that generates stylized images from simple text prompts.

Deploy now

Model details

Developed by
Playground AI
Use case
image generation
Version
v2
Size
Base/medium
Hardware
A10G
License
Playground Community
Readme
View

View repository

Example usage

The model accepts a few main inputs:

prompt: This is text describing the image you want to generate. The output images tend to get better as you add more descriptive words to the prompt.
negative_prompt: Text used to steer the model away from the things you don't want in the output image.

The output JSON object contains a key called output which represents the generated image as a base64 string.

Input
import requests
import os
import base64
from PIL import Image
from io import BytesIO

# Replace the empty string with your model id below
model_id = ""
baseten_api_key = os.environ["BASETEN_API_KEY"]
BASE64_PREAMBLE = "data:image/png;base64,"

# Function used to convert a base64 string to a PIL image
def b64_to_pil(b64_str):
    return Image.open(BytesIO(base64.b64decode(b64_str.replace(BASE64_PREAMBLE, ""))))

data = {
  "prompt": "a futuristic motorcycle, vaporwave neon colors, cyberpunk city, detailed, 8K",
  "negative_prompt": "blurry, low quality",
  "steps": 30
}

# Call model endpoint
res = requests.post(
    f"https://model-{model_id}.api.baseten.co/production/predict",
    headers={"Authorization": f"Api-Key {baseten_api_key}"},
    json=data
)

# Get output image
res = res.json()
output = res.get("output")

# Convert the base64 model output to an image
img = b64_to_pil(output)
img.save("output_image.png")
os.system("open output_image.png")
JSON output
{
    "output": "iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAIAAA..."
}
Preview

Here is another example with a different prompt:

a dreamy landscape with snow capped mountains in the background, clear blue lake in the foreground, surrounded by pine trees

Input
import requests
import os
import base64
from PIL import Image
from io import BytesIO

# Replace the empty string with your model id below
model_id = ""
baseten_api_key = os.environ["BASETEN_API_KEY"]
BASE64_PREAMBLE = "data:image/png;base64,"

# Function used to convert a base64 string to a PIL image
def b64_to_pil(b64_str):
    return Image.open(BytesIO(base64.b64decode(b64_str.replace(BASE64_PREAMBLE, ""))))

data = {
  "prompt": "a dreamy landscape with snow capped mountains in the background, clear blue lake in the foreground, surrounded by pine trees",
  "steps": 40
}

# Call model endpoint
res = requests.post(
    f"https://model-{model_id}.api.baseten.co/production/predict",
    headers={"Authorization": f"Api-Key {baseten_api_key}"},
    json=data
)

# Get output image
res = res.json()
output = res.get("output")

# Convert the base64 model output to an image
img = b64_to_pil(output)
img.save("output_image.png")
os.system("open output_image.png")
JSON output
{
    "output": "iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAIAAA..."
}
Preview