← Back to all generators

ai-forever/kandinsky-2

text2img model trained on LAION HighRes and fine-tuned on internal datasets

Capabilities

1:14:33:416:99:162:33:2Seed

Cost

Community model (estimated from hardware time)

Input Parameters

batch_sizeinteger

Choose batch size. Lower the setting if out of memory.

Default: 1
1234
guidance_scalenumber

Scale for classifier-free guidance

Default: 4min: 1, max: 20
heightinteger

Choose height. Lower the setting if out of memory.

Default: 512
2562884325125767681024
num_inference_stepsinteger

Number of denoising steps

Default: 50min: 1, max: 500
output_formatstring

Format of the output images

Default: "webp"
webpjpgpng
output_qualityinteger

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

Default: 80min: 0, max: 100
prior_cf_scaleinteger
Default: 4
prior_stepsstring
Default: "5"
promptstring

Input Prompt

Default: "red cat, 4k photo"
schedulerstring

Choose a scheduler

Default: "p_sampler"
ddim_samplerp_samplerplms_sampler
seedinteger

Random seed. Leave blank to randomize the seed

widthinteger

Choose width. Lower the setting if out of memory.

Default: 512
2562884325125767681024
Version: 3c6374e7a9a1Updated: 7/25/20266.2M runs