StableDiffusionWebUI: LoRA

Preface

If checkpoint determines the main effect and style of your generated images,

and embeddings mainly serve as negative prompts to avoid undesirable effects,

then LoRA is for fine-tuning to achieve the specific effect you want.

Using LoRA

Installation

Place the downloaded LoRA files into the stable-diffusion-webui/models/Lora directory.

If they don’t appear, click the refresh button on the right side to reload.

Usage

Click on a LoRA under the LoRA tab to use it.

LoRA - Effect

If checkpoint determines the style — whether realistic, cartoon, or something else —

then LoRA determines the content or details.

For example, using the same prompts and parameters as before,

if I want to draw Hinata from Naruto,

I would need a Hinata LoRA.

Positive Prompt

(best quality:1), (high quality:1), detailed/(extreme, highly, ultra/), realistic, 1girl/(beautiful, delicate, perfect/)

Sampler

DPM++ 2M

Sampling Steps

Seed

1199889759

Checkpoint

anythingv5nijimix

LoRA-hinata

Link: https://civitai.com/models/58066/hinata-hinata-hyuga-boruto-naruto-next-generations

Add to prompt: hinata\(boruto\), lora:Hinata\[boruto\]V2:0.8

Summary

In short, Checkpoint determines the style, and LoRA determines the details~

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