Stable Diffusion

Stable Diffusion is a deep learning, text-to-image model released in 2022. It is primarily used to generate detailed images conditioned on text descriptions, though it can also be applied to other tasks such as inpainting, outpainting, and generating image-to-image translations guided by a text prompt.

Getting Started

When selecting the Stable Diffusion plugin, for best performance run it on a ‘g4’ or higher Node Type.
* Select ‘Options’ and choose from the drop down for Node Type

Example Stable Diffusion Usage
Example Stable Diffusion Usage

The Application should launch in a seperate browser window.

Example Stable Diffusion Usage
Example Stable Diffusion Usage

You can enter in whatever text you like in the Prompt field and then Click the Generate Button.

Example Stable Diffusion Usage
Example Stable Diffusion Usage

You can choose a which seed you like by entering a number in the Seed field. This will allow you to receive the same image everytime with the selected word choice. If -1 is entered it will be a random image everytime.

Example Stable Diffusion Usage
Example Stable Diffusion Usage

By default, each image generated is saved under your /stable-diffusion-webui/output/txt2img-images/ folder and can be accessed via ‘File Browser’.

You can download a selected image locally to your desktop by clicking the download button, indicated in the image below.

Example Stable Diffusion Usage
Example Stable Diffusion Usage

Examples

Prompt entered:

‘a detailed full-color pencil drawing of a computer programmer utilizing a terminal that has connected together a network of machines and robotics systems to do his bidding’

Output

Example Stable Diffusion Usage
Example Stable Diffusion Usage

Prompt entered:

‘stained glass of the Buddha under a bodhi tree swarmed by bees’

Output

Example Stable Diffusion Usage
Example Stable Diffusion Usage