And it&

Hires fix 只是以较低的分辨率创建图像，将其放大，然后通过 img2img 发送。请注意，在 ComfyUI 中，txt2img 和 img2img 是同一个节点。Txt2Img 是通过将空图像传递到具有最大降噪的采样器节点来实现的。

A different approach in the space of upscaling, Rather than upscaling the final image, Latent upscaling in the middle of the process can increase the details in an image significantly. I have implemented this idea in the comfy UI workflow and made an 8K image. This workflow is very good for beginners because i have added few useful notes in it. So feel free to use it and post your work and feedback.

I created this first workflow as a semi-beginner, I was inspired by things I saw online, particularly in tutorials on Civitai. I added descriptions of how it works in French and English. The goal is to do image to image in SDXL then upscale before processing in the samplet in order to improve the final result.