Image creation with Kandinsky 2.2
Just describe what you do and don't want, wait a moment, and voila! You'll receive a stunning image, all set to be shared. Kandinsky, the text-to-image AI, specializes in crafting visually captivating images.
Use cases examples
- - Create images for your blog posts
- - Be inspired with architectural photos
Model detail
Kandinsky 2.2
Try it
Examples
Input
{"input":{"prompt":"a blue car, futuristic, well d...""negative_prompt":"width":512"height":512"num_inference_steps":75"num_inference_steps_prior":25"num_outputs":1"seed":8093}"id":83}
Output
{"status":"succeeded""output":[0:"https://rbqktisnztholqojxlaf.s..."]"prediction_time":6.175243}
API Information
Input description
Input prompt
Default value: A moss covered astronaut with a black background
Specify things to not see in the output
An enumeration.
Default value: 512
Enum values: 384, 512, 576, 640, 704, 768, 960, 1024, 1152, 1280, 1536, 1792, 2048
An enumeration.
Default value: 512
Enum values: 384, 512, 576, 640, 704, 768, 960, 1024, 1152, 1280, 1536, 1792, 2048
Number of denoising steps
Default value: 75
Number of denoising steps for priors
Default value: 25
Number of images to output.
Default value: 1
Random seed. Leave blank to randomize the seed
Output JSON Schema
This represents the JSON schema that details the structure of the model's output.