Drawing Avatars with Stable Diffusion

Most of this post is based on this video

Intro

Resources used:

1. Stable Diffusion integrated package: https://www.bilibili.com/read/cv22159609/
2. Stable Diffusion model: https://tusi.cn/models/605039709506335625
3. LoRA model: https://tusi.cn/models/620507699483853069

How to do it

1. First, pick a suitable photo — clear subject, clear content, no fine details needed. Here's the photo I picked:

   

2. Following the video, paste these prompts into img2img:

   PROMPTCopy

   (white background:1.1),(simple background:1.1),(chibi),thick outline,happy,mugshot
   

3. Import the photo into WD 1.4 Tagger and you'll get these tags:

   PROMPTCopy

   outdoors, ocean, solo, day, black hair, 1boy, from behind, male focus, horizon, water, shorts, sky, photo background, rock, scenery, holding, short hair, standing, facing away, blue sky, pants, white shorts, long sleeves, shirt, shoes, bag, backpack, wide shot
   

4. Paste these tags into img2img, removing the ones you don't need.

5. Upload the image in the img2img tab and change the following parameters:

   Parameter	Value
   Sampler	DPM++ 3M SDE
   Steps	30
   Denoising strength	0.7
   Batch count	4

6. Click Generate to create 4 images. You can adjust the denoising strength based on the results — a value between 0.6-0.7 usually works — until you get an image you like.

7. Send the image you like and its generation parameters to the Extras tab, set both Upscaler 1 and Upscaler 2 to R-ESRGAN 4x+ Anime6B, set Scale by to 4, and click Generate.

8. In the end, I got this image:

   

Let's compare: