Model input

prompt

Input prompt

negative_prompt

Specify things to not see in the output

width

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

height

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

num_inference_steps

Number of denoising steps (minimum: 1; maximum: 50)

guidance_scale

Scale for classifier-free guidance (minimum: 1; maximum: 20)

scheduler

Choose a scheduler.

seed

Random seed. Leave blank to randomize the seed

Text-to-image

realisticdreams

This model was trained on 100,000 photos of real people and will deliver any character your imagination can create.

1.7k

Model result

Download