Stable Diffusion (image2image)

Image+text-2-image

Stable Diffusion (image2image): SD 1.5 and SD XL

Using a start image you can create a new AI artwork based on the composition of your original image

Quick menu: click on any section to quickly go to it

Key features

Step by step tutorial

Parameters description

Key features

Takes the resolution of Start image
Up to 2048x2048
Stable Diffusion 1.5 and XL
Available with 2 state-of-the-art models: Stable Diffusion 1.5 and Stable Diffusion XL
Wide choice of custom models
With custom checkpoints (Styles or models) you can transform your image into any available style
Perfect for variations
Using image 2 image pipeline you can create quick variations of any image or photo
Basic and advanced settings
Tweak how much you would want the Start image to change in your generation

How to use the node

Click on each step to see the corresponded image as an example and tutorial to follow

1. Upload your image and connect to the node
If you're using your photo or any side image, just drag and drop it to the workspace.
You can also connect the image from other nodes
2. Type your prompt
If you're looking for creating variations from another node, simply copy it and paste it here.
If you're using your photo or reference as in our example, briefly describe what's on your image and add relevant keywords.
Use ChatGPT in the bottom right corner to get more keywords or a Prompt Extend node.
3. Set Start Image skip
This parameter defines how close to the Start image the final generation will be.
We recommend to set it to 0,4 if you're creating variations
Or 0,5 if you're using the image as a reference
4. Press Launch
If you don't like the results, simply press Start button again to get different images

1. Upload your image and connect to the node
If you're using your photo or any side image, just drag and drop it to the workspace.
You can also connect the image from other nodes
We recommend upscaling your image to 1024x1024 for better results
2. Type your prompt
If you're looking for creating variations from another node, simply copy it and paste it here.
If you're using your photo or reference as in our example, briefly describe what's on your image and add relevant keywords.
Use ChatGPT in the bottom right corner to get more keywords or a Prompt Extend node.
3. Set Denoising strength (Start Image Skip)
This parameter defines how close to the Start image the final generation will be.
We recommend to set it to 0,4 if you're creating variations
Or 0,5 if you're using the image as a reference
4. Press Launch
If you don't like the results, simply press Start button again to get different images

Need inspiration for prompts?

Check out our prompt collection!

Explore prompts

Parameters

The parameters are all similar to the general Stable Diffusion parameters (for reference, visit this page) . The main parameter that you might want to change is Start image skip

Start image skip

Range: from 0.05 to 0.95
Available in Stable Diffusion 1.5 and Stable Diffusion XL (img2img)

It defines how close to the Start image the final image will be.
The higher the number is, the more different from the Start image a generated artwork will be.

We recommend to keep it between 0,6-0,7 if you use Start image