Image *

Input image

Prompt

Input prompt 0.5 tokens per audio usage.

Negative prompt

Specify things to not see in the output 0.5 tokens per audio usage.

Num inference steps

0

30

100

Number of diffusion steps

Adapter conditioning scale

0

1

5

Conditioning scale

Adapter conditioning factor

0

1

1

Factor to scale image by

Guidance scale

0

7.5

10

Guidance scale to match the prompt

Num samples

1

1

4

Number of outputs to generate

Scheduler

Which scheduler to use

Random seed

Random seed for reproducibility, leave blank to randomize output

Select Language

Select the language for the output
Please provide all required parameters (* marked)

Output