The presenter compares examples of Nvidia Pixel Diffusion upscaling and discusses its use of pixel-space denoisingA diffusion model generates or transforms data by learning to reverse a gradual noising process, often through a sequence of denoising steps.. Performance and quality comparisons are presented as the presenter’s observations.
The tutorial walks through three ComfyUI workflows: upscaling an existing image, generating an image with another model before upscaling it, and generating an image directly with the diffusion model. It discusses model selection, resolution and installation steps.
Watch on YouTube
