Consistent Characters in Stable diffusion Same Face and Clothes Techniques and tips

preview_player
Показать описание
#ai #stablediffusion #a1111 #afterdetailer #fashion #aiimages #character #consistent #consistency #controlnet

We can define a Consistent Character as a person who has same face, same clothes, in different poses and different backgrounds.

00:00:00 introduction and sample results
00:00:34 consistent face techniques using custom names
00:01:50 putting the face description in after detailer
00:02:15 mixing different character LoRAs to create new character
00:03:00 using Roop ( ReActor is newere better extension)
00:04:30 improving consistency with Controlnets (Reference).. (update: now IP Adapter could be a better option)
00:07:28 multiple controlnets, open pose (update: dw openpose is now better) and reference controlnet (update IP Adapter might be better now)
00:08:24 using LoRAs to increase consistency

Now! Creating 100% consistent Character in Stable diffusion is impossible, because SD is inconsistent by design…. To Create 100% consistent characters/clothes, you should use Blender or Other 3D software tools, not Stable diffusion.
However! it is possible to achieve high level of consistency like 90%, which can be convincing enough.
This video will explain
1- how to produce the same face for unlimited number of images with and without LoRAs and using random seeds.
2- How to produce almost the same clothes with same face in different poses and backgrounds.

Techniques covered: use of After detailer, Reference controlnet, use of Roop, tips of getting better consistent clothes, and shows what is possible and what is not.

Computer Specs:
Laptop: Legion 5 Pro
Processor :AMD Ryzen 7 5800H , 3201 Mhz
System RAM: 16.0 GB
Graphics GPU: NVIDIA GeForce RTX 3070 Laptop GPU 8GB
Рекомендации по теме
Комментарии
Автор

At last a good video without bad edited "fx" or exhibition of unwanted skills by the presenter! Thank you, I'm following your channel.

ClaudioMalagrino
Автор

Thank you so much for such a clear tutorial!

timothywells
Автор

This is the video I have been looking for!

mitch
Автор

did you remove the background and generate almost the same background? anyway thanks for the video.

RockG.o.d
Автор

Very nice video!
I have two questions. Are you using SD on your PC or is it online version? What do you mean to use blender to have the same consistency? Like to use some Ai plugin in blender or just model the whole thing? Thx

loquiman
Автор

This is so helpful video, thank you! My UI is not same as your UI. So which extansion or models do you use? can you share the links that you have?

GürayKorkut
Автор

hai bro,
can you make video about changing everything (inpaint anything) except the subject, (include the cloth and pose) please ^^

DeFirm-
Автор

Can you show us a video about good prompts? or is there recommended links about good prompts?

stepphen_ffc
Автор

Great video. Can you share some of your prompts ?

Hooooodad
Автор

Great Video, I manage to get the same face each time, but how can I save the face for future use?
Seems like once I close the program I can no longer regenerate the same face again?
Any help would be greatly appreciated, keep up the amazing work!

dannynguyen
Автор

How do you get such great looking hands?

vektordx
Автор

8:16 the ui tells me the batch directory is unfindable. Mine starts with C: and not E:, but overall seems similar to yours. Any ideas?

Your video is very informative, thanks

jamesc.
Автор

Between prompting, lora, embedding and dreambooth model trained on a single person with single clothing, which method would give you the most consistent results when using high denoising in img2img?

aiartbx
Автор

You missed the part that you set the batch count to 30 in order to get the same face on all 30 images

stanleywtang
Автор

For better results we should use what? Splinter and what else did you say

Hshjshshjsj
Автор

Hi, excellent videos! However what I need is I think a mix of several techniques. Is there a way to contact your for more details? I'd like to have a call if you're open to something like that. Thank you.

mach_j
Автор

Hello, how can I have the same openpose patch as you?

cutelkw
Автор

what if we refreshed the page, does after detailer going to save the prompt to generate consistent character? if not how do we do that?

gilgameshgaming
Автор

i have a T-Shirt design in which there are some certain designs .. but Im not able to get those designs on Models clothes its just clothes that been referred.. Can you help me with that?

ggrrr
Автор

If you already have other photos as jpgs, how do you change the skirts in one photo, and then apply those skirts to the models in the other jpgs?

타오바오-hl