Image Generation

Create stunning images from text descriptions. Photorealistic, artistic, or anything you can imagine.

Capabilities

🖼️

Generate

Create original images from text prompts in any style

✏️

Edit

Modify parts of existing images using natural language

🔄

Variations

Create similar versions of an existing image

Quick Start

Python
from mythicdot import MythicDot

client = MythicDot()

# Generate an image
response = client.images.generate(
    model="mythic-image-3",
    prompt="A white cat sitting on a velvet couch, oil painting style",
    size="1024x1024",
    quality="hd",
    n=1
)

# Get the image URL
image_url = response.data[0].url
print(image_url)

# Or get base64-encoded image
response = client.images.generate(
    model="mythic-image-3",
    prompt="A white cat sitting on a velvet couch",
    response_format="b64_json"
)

image_data = response.data[0].b64_json

Edit Images

Modify specific areas of an image using a mask:

Python
# Edit an existing image
response = client.images.edit(
    model="mythic-image-3",
    image=open("photo.png", "rb"),
    mask=open("mask.png", "rb"),
    prompt="Add a red hat",
    size="1024x1024"
)

💡 Mask Tips

The mask should be a PNG with transparent areas where you want edits. Fully transparent = edit area, opaque = keep original.

Parameters

Parameter Type Description
prompt required string Text description of the desired image (max 4000 chars)
model string mythic-image-3 (default) or mythic-image-3-hd
size string 1024x1024, 1024x1792, or 1792x1024
quality string standard (default) or hd
n integer Number of images (1-10)
style string vivid (default) or natural
response_format string url (default) or b64_json

Styles

🎨

Vivid

🌿

Natural

Artistic

📷

Photo

Pricing

1024×1024
$0.04
per image (standard)
1024×1792
$0.08
per image (standard)
HD Quality
$0.12
per image (1024×1024)

Prompt Best Practices