Ugly Hedgehog - Photography Forum
Home Active Topics Newest Pictures Search Login Register
AI Artistry and Creation
Theresa 3.0
Page 1 of 2 next>
Jul 10, 2023 08:48:15   #
jlg1000 Loc: Uruguay / South America
 
With the new SDXL 9.0, I decided to upgrade Theresa to 3.0 and let her model for me

Wanted to make them look like retro steampunk paintings I used to see on book covers when I was a teenager.

Hope you like the "photoshoot"













Reply
Jul 11, 2023 12:44:10   #
Curmudgeon Loc: SE Arizona
 
AI is fun to play with. The problem I have is that in both MidJourny or Stable Diffusion is getting a full body shot, success rate < 50%. Looks like SDXL 9.0 has the same problem

Reply
Jul 11, 2023 22:50:51   #
jlg1000 Loc: Uruguay / South America
 
Curmudgeon wrote:
AI is fun to play with. The problem I have is that in both MidJourny or Stable Diffusion is getting a full body shot, success rate < 50%. Looks like SDXL 9.0 has the same problem


Well... I can do full body:

I'm putting this imagen on a separarte post also



Reply
 
 
Jul 12, 2023 14:08:54   #
Curmudgeon Loc: SE Arizona
 
Not quite. No legs or feet

Reply
Jul 12, 2023 14:16:10   #
jlg1000 Loc: Uruguay / South America
 
Curmudgeon wrote:
Not quite. No legs or feet


Right... trying to do better

Reply
Jul 12, 2023 14:41:50   #
Curmudgeon Loc: SE Arizona
 
jlg1000 wrote:
Right... trying to do better


Seems to be an issue with most, if not all, of the AI software. My best luck has been using: full body shot, standing and changing the orientation to portrait. I sometimes get 2 out of 4 images in MidJourney and not quite that good in Stable Diffusion. I have given up on Firefly

Reply
Jul 12, 2023 17:09:42   #
jlg1000 Loc: Uruguay / South America
 
Curmudgeon wrote:
Seems to be an issue with most, if not all, of the AI software. My best luck has been using: full body shot, standing and changing the orientation to portrait. I sometimes get 2 out of 4 images in MidJourney and not quite that good in Stable Diffusion. I have given up on Firefly



Reply
 
 
Jul 16, 2023 23:10:28   #
jlg1000 Loc: Uruguay / South America
 
Curmudgeon wrote:
Seems to be an issue with most, if not all, of the AI software. My best luck has been using: full body shot, standing and changing the orientation to portrait. I sometimes get 2 out of 4 images in MidJourney and not quite that good in Stable Diffusion. I have given up on Firefly


I think I've got it.

You need to give space to the model.





Reply
Jul 17, 2023 00:31:16   #
Curmudgeon Loc: SE Arizona
 
Please explain how to give more space to the model. I use portrait orientation.

Reply
Jul 17, 2023 07:45:29   #
jlg1000 Loc: Uruguay / South America
 
Curmudgeon wrote:
Please explain how to give more space to the model. I use portrait orientation.


By selecting the adequate WxH ratio for the desired composition.

For example:
1) a full body man or woman needs about 1:2 ratio.
2) Because the model I've chosen has 512px resolution, that means that *one side must be 512 px*
3) Therefore, the other side must have 512 x 2 = 1024 px (aprox.)

Therefore, by choosing 512 px W x 1024 px H, I get the full body composition.

There are other techniques, like segmenting, which I'm investigating right now.



Reply
Jul 17, 2023 19:45:14   #
Curmudgeon Loc: SE Arizona
 
Thanks

Reply
 
 
Jan 13, 2024 00:16:48   #
Bill Hancock Loc: Wausau, WI
 
How are able to get the same face and different body positions? I can never get the same face with Adobe Fire Fly. I would like to know if you don't mind sharing the information.

Reply
Jan 13, 2024 00:27:34   #
Bill Hancock Loc: Wausau, WI
 
How are able to get the same face and different body positions? I can never get the same face with Adobe Fire Fly. I would like to know if you don't mind sharing the information.

Reply
Jan 19, 2024 15:06:11   #
jlg1000 Loc: Uruguay / South America
 
Bill Hancock wrote:
How are able to get the same face and different body positions? I can never get the same face with Adobe Fire Fly. I would like to know if you don't mind sharing the information.


Sure I can.
I'm running open source Comfy UI which in term interfaces with a highly modded Stable Diffusion version in my own Linux computer. I even wrote pieces of the software.
Please note: I do not use any of the "online services"









Reply
Jan 19, 2024 15:11:21   #
jlg1000 Loc: Uruguay / South America
 
Bill Hancock wrote:
How are able to get the same face and different body positions? I can never get the same face with Adobe Fire Fly. I would like to know if you don't mind sharing the information.


You'll have to install Stable Diffusion: https://github.com/CompVis/stable-diffusion
Comfy UI: https://github.com/comfyanonymous/ComfyUI
Download and install a bunch of custom models, nodes, etc.
Maybe - just maybe - learn some coding (not mandatory)

Start by watching this...
https://www.youtube.com/watch?v=AbB33AxrcZo&ab_channel=ScottDetweiler
https://www.youtube.com/watch?v=LNOlk8oz1nY&ab_channel=OlivioSarikas
... and go down the rabbit hole

Reply
Page 1 of 2 next>
If you want to reply, then register here. Registration is free and your account is created instantly, so you can post right away.
AI Artistry and Creation
UglyHedgehog.com - Forum
Copyright 2011-2024 Ugly Hedgehog, Inc.