← Back to all generators
ai-forever/kandinsky-2.2
OfficialView on Replicate →
multilingual text2image latent diffusion model
Capabilities
1:14:33:416:99:162:33:2Negative PromptSeed
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
height | integer | Height of output image. Lower the setting if hits memory limits. | 512 | 384512576640704768960102411521280153617922048 |
negative_prompt | string | Specify things to not see in the output | — | — |
num_inference_steps | integer | Number of denoising steps | 75 | min: 1, max: 500 |
num_inference_steps_prior | integer | Number of denoising steps for priors | 25 | min: 1, max: 500 |
num_outputs | integer | Number of images to output. | 1 | min: 1, max: 4 |
output_format | string | Output image format | "webp" | webpjpegpng |
prompt | string | Input prompt | "A moss covered astronaut with a black background" | — |
seed | integer | Random seed. Leave blank to randomize the seed | — | — |
width | integer | Width of output image. Lower the setting if hits memory limits. | 512 | 384512576640704768960102411521280153617922048 |
heightintegerHeight of output image. Lower the setting if hits memory limits.
Default:
512384512576640704768960102411521280153617922048
negative_promptstringSpecify things to not see in the output
num_inference_stepsintegerNumber of denoising steps
Default:
75min: 1, max: 500num_inference_steps_priorintegerNumber of denoising steps for priors
Default:
25min: 1, max: 500num_outputsintegerNumber of images to output.
Default:
1min: 1, max: 4output_formatstringOutput image format
Default:
"webp"webpjpegpng
promptstringInput prompt
Default:
"A moss covered astronaut with a black background"seedintegerRandom seed. Leave blank to randomize the seed
widthintegerWidth of output image. Lower the setting if hits memory limits.
Default:
512384512576640704768960102411521280153617922048
Version:
ad9d7879fbffUpdated: 8/1/202610.1M runs
cinemasetfree