Conditioning parameters are actually helping to get better picture now
Runtime profile
Source description
Total rework.
Conditioning parameters are actually helping to get better picture now
Introducing Conditioning Scale
Single node from ComfyMath intsead of giant math group
Crop forces resize
Compact layout
Remaining hardware or download-size estimates are not available yet.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use this ComfyUI workflow to generate an SDXL image from an input image and prompt; its image-size-aware conditioning is 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.
Inputs are an image and prompt; you can choose whether to resize the image, and the output is a generated image.
Install WAS Node Suite and ComfyMath custom nodes, then download and open the workflow.
The model files named for the workflow are `sd_xl_base_1.0.safetensors` and `sdxl_vae.safetensors`; check that both are available in your ComfyUI setup.
Suggestion · not verified
Conditioning Scale is optional; the description says it can make the output look bigger or higher resolution.
For txt2img-style generation, set denoise to 1.0; the workflow description says this retains size-guiding benefits.
If you have version 1.0, the publisher advises updating to v2.0 and says not to use the earlier version.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource context: 5827 downloads · Type Workflows · Base model SDXL 1.0
Requirements
Checkpoint · 6.46 GB · SAFETENSORS · fp16 · pruned · Civitai · 101055
VAE · 319 MB · Hugging Face · stabilityai/sdxl-vae
Source context: 5818 downloads · Type Workflows · Base model SDXL 1.0
Source context: 5385 downloads · Type Workflows · Base model SDXL 1.0