🎨 Image-to-Image Generation (img2img)
Image-to-image (img2img) generation is a powerful feature that allows you to transform an existing image based on a new prompt or specific parameters. Instead of generating an image from scratch, you provide an input image, and the AI uses it as a foundation to create a new visual. This is incredibly useful for style transfer, image variations, or modifying existing assets while maintaining their core composition.
How it Works:
With img2img, the AI takes both a textual prompt and an input image. The strength
parameter plays a crucial role here, determining how much the generated image deviates from the original input image. A higher strength
value means the AI will take more creative liberties, while a lower value will result in an output closer to the original.
Example: Transforming a Landscape
Let's say you have an image of a serene forest and you want to transform it into a mystical, glowing forest. You would provide the original forest image and a prompt like "a mystical forest, glowing flora, ethereal light."
cURL
curl -X POST \
-u "YOUR_API_KEY:YOUR_API_SECRET" \
-H "Content-Type: application/json" \
-d
'{
"prompt": "a mystical forest, glowing flora, ethereal light",
"imageUrl": "https://example.com/your-forest-image.jpg", # URL of your input image
# you can also use image, using an assetId
"strength": 0.75,
"numSamples": 1,
"guidance": 3.5,
"numInferenceSteps": 28,
"modelId": "flux.1-dev"
}' \
https://api.scenario.com/v1/generate/img2img
Python
import requests
api_key = "YOUR_API_KEY"
api_secret = "YOUR_API_SECRET"
url = "https://api.scenario.com/v1/generate/img2img"
headers = {"Content-Type": "application/json"}
payload = {
"prompt": "a mystical forest, glowing flora, ethereal light",
"imageUrl": "https://example.com/your-forest-image.jpg", # URL of your input image
# you can also use image, using an assetId
"strength": 0.75,
"numSamples": 1,
"guidance": 3.5,
"numInferenceSteps": 28,
"modelId": "flux.1-dev"
}
response = requests.post(url, headers=headers, json=payload, auth=(api_key, api_secret))
## you need to handle the evolution of the job
if response.status_code == 200:
data = response.json()
print("Image generation successful!")
print("Generated Image ID:", data["metadata"]["assetIds"][0])
else:
print(f"Error: {response.status_code} - {response.text}")
Updated 6 days ago