stability-ai/stable-diffusion

A latent text-to-image diffusion model capable of generating photo-realistic images given any text input

Input
Configure the inputs for the AI model.

Random seed. Leave blank to randomize the seed

Width of generated image in pixels. Needs to be a multiple of 64

Height of generated image in pixels. Needs to be a multiple of 64

Input prompt

Choose a scheduler.

1
4

Number of images to generate.

1
20

Scale for classifier-free guidance

Specify things to not see in the output

1
500

Number of denoising steps

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.