StableDiffusionWebUI: High-Resolution Fix (Hires.fix) - Denoising Strength

Preface

The previous section introduced the algorithm differences in Hires.fix: https://blog.vincentqiao.com/sd-hiresfix-m

This section covers the denoising strength parameter of Hires.fix.

Hires.fix

We keep other parameters fixed for comparison.

Prompt - Chinese

一个男孩，坐在椅子上，上半身，靠近窗口，蓝色上衣，黑色头发，戴眼镜，面向镜头，左手边是窗子

Prompt - English

A boy sitting on a chair, upper body, close to the window, blue shirt, black hair, wearing glasses, facing the camera, with the window on his left side

Checkpoint

Samaritan 3d Cartoon

Seed

3255625742

Sampler

Euler a

Sampling Steps

Algorithm

Latent

Denoising Strength - 0.1

Denoising Strength - 0.3

Denoising Strength - 0.5

Denoising Strength - 0.7

Denoising Strength - 1.0

Summary

The recommended denoising strength for Hires.fix is around 0.7.

Too low causes blurriness, while too high introduces unexpected content.

SDWebUI

|—Link: https://sdwebui.ai/?from=vq

|—Authentic Stable Diffusion WebUI V1.10.1~

|—Top-tier 4090 GPU, premium members get exclusive single 4090 card for image generation~

|—Supports Mac client, Windows client, and Web online usage~

|—Innovative instant model transfer feature, instantly use local models~

|—Supports txt2img, img2img, extras, and PNG info

|—Supports CLIP interrogation and DeepBooru interrogation

|—Supports Hires.fix with 21 built-in upscaling models

|—Supports ADetailer with 11 built-in repair models

|—Supports ControlNet with 44 built-in preprocessors and 68 built-in models

|—Supports super-resolution upscaling (Tiled Diffusion, Demo Fusion, Tiled VAE)

|—Supports old photo restoration with 21 built-in upscaling models, plus GFPGAN and CodeFormer restoration models

|—Built-in 2 common Styles, 11 popular Checkpoint models, 7 popular LoRA models, 14 common embeddings

|—Built-in oldsix prompt plugin

|—Built-in 23-lesson beginner tutorial