stable-image/upscale
Takes images between 64x64 and 1 megapixel and upscales them all the way to 4K resolution. Put more generally, it can upscale images ~20-40x times while preserving, and often enhancing, quality.
How to use
- Invoke this endpoint with the required parameters to start a generation
- Use that
idin the response to poll for results at the upscale/result/ endpoint- Rate-limiting or other errors may occur if you poll more than once every 10 seconds
Price
Flat rate of 25 cents per generation.
Authorizations
Use your Stability API key to authentication requests to this App.
Headers
Your Stability API key, used to authenticate your requests. Although you may have multiple keys in your account, you should use the same key for all requests to this API.
1The content type of the request body. Do not manually specify this header; your HTTP client library will automatically include the appropriate boundary parameter.
1"multipart/form-data"
Body
The image you wish to upscale.
Supported Formats:
- jpeg
- png
- webp
Validation Rules:
- Every side must be at least 64 pixels
- Total pixel count must be between 4,096 and 1,048,576 pixels
What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.
To control the weight of a given word use the format (word:weight),
where word is the word you'd like to control the weight of and weight
is a value between 0 and 1. For example: The sky was a crisp (blue:0.3) and (green:0.8)
would convey a sky that was blue and green, but more green than blue.
1 - 10000A blurb of text describing what you do not wish to see in the output image. This is an advanced feature.
10000Dictates the content-type of the generated image.
jpeg, png, webp A specific value that is used to guide the 'randomness' of the generation. (Omit this parameter or pass 0 to use a random seed.)
0 <= x <= 4294967294Indicates how creative the model should be when upscaling an image. Higher values will result in more details being added to the image during upscaling.
0.1 <= x <= 0.5Guides the image model towards a particular style.
enhance, anime, photographic, digital-art, comic-book, fantasy-art, line-art, analog-film, neon-punk, isometric, low-poly, origami, modeling-compound, cinematic, 3d-model, pixel-art, tile-texture Response
Upscaling was successful!
The id of a generation, typically used for async generations, that can be used to check the status of the generation or retrieve the result.
64"a6dc6c6e20acda010fe14d71f180658f2896ed9b4ec25aa99a6ff06c796987c4"