Create consistent characters with Stable diffusion!!

Описание к видео Create consistent characters with Stable diffusion!!

Create your own consistent characters with Stable Diffusion! Even training a LORA to use it however you want.

Join our Discrod server-   / discord  
to learn & help about this and more!

References used in the video:
https://drive.google.com/file/d/1-XOM...

------------ Links used in the VIDEO ---------

Lora training and intall guide:
   • LORA training EXPLAINED for beginners  

DynamicPrompts Extension: https://github.com/adieyal/sd-dynamic...

CharacterTurner Emb: https://civitai.com/models/3036/chart...

Detail Tweaker LORA: https://civitai.com/models/58390/deta...

MoreDetails LORA: https://civitai.com/models/82098/add-...

TagManager(BDTM_V1.6.5_NetCore60_AllInclude): https://github.com/starik222/BooruDat...

------------ Social Media ---------


-Instagram:   / not4talent_ai  
-Twitter:   / not4talent  


Make sure to subscribe if you want to learn about AI and grow with the community as we surf the AI wave :3


#aiairt #digitalart #automatic1111#stablediffusion #ai #free #tutorial #betterart #goodimages #sd #digitalart #artificialintelligence #inpainting #outpainting #img2img
#consistentCharacters #characters #characterdesign #personaje #midjourney

0:00 intro
0:11 Problem
0:30 Basic current Solution
0:54 Our first step
1:04 Making OpenPose Refs
1:45 Our Character
1:56 Base SpreadSheet
2:30 Hires Fix the result
3:00 Objective
3:13 Easy tricks (variations)
3:42 Secure a White BG
4:10 Creating new poses
4:48 Next step
4:58 comic example
5:12 Clean up
6:55 Clean up realistic
7:25 Upscaling
9:05 Regularization images
9:45 Dynamic Prompts
10:42 Prompts script
10:52 Using wildcards
11:22 Second Step
11:38 Dataset Example
11:56 Roop Fixing
12:06 Fixing and cleaning
12:30 Separating the poses
13:48 Creating compositions
14:42 Make Light variations
15:00 Blur and extra steps
15:14 Examples
15:40 Make it however
16:08 Final Step
16:20 KohyaSS needed
16:48 Renaming
17:05 Tagging
18:30 Realistic style captions
18:46 Training Folders
19:15 Model Choosing
19:37 training parameters
21:30 Sample image steps
22:20 IMPORTANT STUFF
22:45 DISCROD SERVER
23:25 Results
23:50 Improve results infinitely
24:06 Change the LORA's style
24:23 Limits
24:40 Realistic Stress Test
25:20 Prototype idea
25:40 Possible solutions
26:25 Lets Work together!
26:38 Ty for watching

Комментарии

Информация по комментариям в разработке