← Back to all generators

ai-forever/kandinsky-2.2

multilingual text2image latent diffusion model

Capabilities

1:14:33:416:99:162:33:2Negative PromptSeed

Cost

Community model (estimated from hardware time)

Input Parameters

heightinteger

Height of output image. Lower the setting if hits memory limits.

Default: 512
384512576640704768960102411521280153617922048
negative_promptstring

Specify things to not see in the output

num_inference_stepsinteger

Number of denoising steps

Default: 75min: 1, max: 500
num_inference_steps_priorinteger

Number of denoising steps for priors

Default: 25min: 1, max: 500
num_outputsinteger

Number of images to output.

Default: 1min: 1, max: 4
output_formatstring

Output image format

Default: "webp"
webpjpegpng
promptstring

Input prompt

Default: "A moss covered astronaut with a black background"
seedinteger

Random seed. Leave blank to randomize the seed

widthinteger

Width of output image. Lower the setting if hits memory limits.

Default: 512
384512576640704768960102411521280153617922048
Version: ad9d7879fbffUpdated: 8/1/202610.1M runs