Eachlabs | AI Workflows for app builders

Sana by Nvidia

Used Model: sana

Sana, a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution

Public IconPublic
License IconLicense
Demo IconDemo
Num Inference Steps

Number of denoising steps

18
Pag Guidance Scale

PAG Guidance scale

2
Negative Prompt

Specify things to not see in the output

Enter your negative prompt
Guidance Scale

Classifier-free guidance scale

5
Prompt

Input prompt

a cyberpunk cat with a neon sign that says "Sana"
Height

Height of output image

1024
Width

Width of output image

1024
Seed

Random seed. Leave blank to randomize the seed

Enter your seed
Result

Preview, share or download. Again with one click.

Preview