ai-forever/kandinsky-2

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

Input
Configure the inputs for the AI model.

Random seed. Leave blank to randomize the seed

Choose width. Lower the setting if out of memory.

Choose height. Lower the setting if out of memory.

Input Prompt

Choose a scheduler

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

Format of the output images

1
20

Scale for classifier-free guidance

0
100

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

0
100
1
500

Number of denoising steps

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.

kandinsky-2 - ikalos.ai