Basic uses of stable diffusion
Corresponding video
- https://www.bilibili.com/video/BV1Q14y1f7XJ/
- https://www.bilibili.com/video/BV1av4y1E74C/
1. Download
1.1 Official github:
Official github:
- GitHub - Stability-AI/stablediffusion: High-Resolution Image Synthesis with Latent Diffusion Models
- GitHub - AUTOMATIC1111/stable-diffusion-webui: Stable Diffusion web UI
The official download and installation is very troublesome.
1.2 Download the integration package
Author: Akiba aaaki's personal space_bilibili_bilibili
Download the stablediffusion toolkit through the network disk .
V4 version download:
Link: https://pan.quark.cn/s/39c25d1cda63
Extraction code: 6wYT
2. Installation
- Install launcher running dependencies
- Unzip sd-webui-aki-v4.zip
- After A launcher.exe
enters the launcher, update the latest stable version! ! !
Also update all plug-ins to the latest version! ! !
- Then start it with one click.
- Access http://127.0.0.1:7860/ with the browser, and the interface is as shown below.
3. Basic introduction to the interface
3. Test – Vincentian Diagram
-
Select main model
-
Vincent diagram – enter prompt words (forward, reverse)
**注意：目前仅支持英文提示词。**
例如：https://civitai.com/images/500009?modelVersionId=46137&prioritizedUserIds=141871&period=AllTime&sort=Most+Reactions&limit=20
正向提示词：upper body, 1girl, white hair, ponytail, purple eyes, (ninja), short sword, medium breats ,scarf, wallpaper, magic circle background, light particles, blue fire,
上半身，1个女孩，白发，马尾辫，紫色的眼睛，(忍者)，短剑，中等胸，围巾，壁纸，魔法圈背景，光粒子，蓝色火焰，
反向提示词：(worst quality:2, low quality:2), (zombie, sketch, interlocked fingers, comic),
(最差质量:2，低质量:2)，(僵尸，小品，手指交叉，漫画)，
- Configuration parameters: number of iterations, adoption method, image wh, batch, single batch quantity, prompt word guidance coefficient, random seed
- generate
- Effect:
