SDXL img2img (automatic aspect ratio) | ComfyUI workflow — v2.0

Use the SDXL img2img ComfyUI workflow to generate an image from an input image and prompt, with image-size-aware conditioning intended to guide composition, keep objects in frame, and create a higher-resolution look.

Select an image for img2img, choose whether to resize it, optionally set Conditioning Scale, then queue the prompt.

You can choose whether to resize the input image; the generated image is guided toward a higher-resolution look, with objects kept in frame and composition guided.

Install WAS Node Suite and ComfyMath custom nodes, then download and open the workflow.

The listed model filenames are `sd_xl_base_1.0.safetensors` and `sdxl_vae.safetensors`.

Conditioning Scale is optional; the description says it can make the output look bigger or higher resolution.

For txt2img-style use, try denoise at 1.0; the description presents this as regular txt2img use with size-guiding benefits.

Suggestion · non vérifié

If you have version 1.0, the publisher advises updating.