SDXL conditioning can contain image size! This workflow takes this into account, guiding generation to:

• Look like higher resolution images

• Keep objects in frame

• Guide image composition to make sense

Installation and dependencies

1. Install WAS Node Suite custom nodes;

2. Instal ComfyMath custom nodes;

3. Download and open this workflow.

How to use

1. Select image for img2img;

2. Choose to resize or not;

3. (optional) Choose Conditioning Scale. It can make your output look like bigger, higher resolution image;

4. Queue Prompt.

Pro Tip: You can set denoise to 1.0 to use the workflow as usual txt2img, but with size guiding benefits.

Note

I made some research and find out that v1.0 version of the workflow was total bullshit 😅. If you downloaded previous version, don't use it. Better update.

Check out my other workflows