Stable Diffusion

Stable Diffusion is a text-to-image diffusion model capable of generating photo-realistic images given any text input. You can learn more about the model here.

You can generate images using Stable Diffusion by using the "Create Prediction - Stable Diffusion" workflow action.

It requires the following inputs:

Input	Type of Field	Description
Prompt	Text	The text prompt you're using to create the image(s)
Height	Number (integer)	The height of the image(s) you want to create
Width	Number (integer)	The width of the image(s) you want to create
Number of Outputs	Number (integer)	The number of images you want to create with each prediction. Must be between 1 and 4.
Negative Prompt	Text	Things you do NOT want to see in the output image(s)
# Inference Steps	Number (integer)	The number of denoising steps used in the prediction (minimum: 1; maximum: 500). In general, the more steps you use the more detailed the output. However, the more steps you use the longer it will take to generate the prediction.
Guidance Scale	Number (decimal)	Scale for classifier-free guidance (minimum: 1; maximum: 20)
Seed	Number (integer)	Random seed. Leave blank to randomize the seed
Scheduler	Text (list of pre-defined options)	The type of scheduler you want to use.
Version	Text (list of pre-defined options)	The version of Stable Diffusion you want to use. I've found the default version (a9758cbfbd5f3c2094457d996681af52552901775aa2d6dd0b17fd15df959bef) works better than the newer version (ac732df83cea7fff18b8472768c88ad041fa750ff7682a21affe81863cbe77e4)