Lorthard
Newbie
- Aug 19, 2017
- 69
- 1,119
Which version do you prefer:
Dream Shaper (With custom Lora's)
Orange Mix (With Custom Lora's)
Dream Shaper (With custom Lora's)
You don't have permission to view the spoiler content.
Log in or register now.
Orange Mix (With Custom Lora's)
You don't have permission to view the spoiler content.
Log in or register now.
Last edited:
Ludvinae
Member
- Sep 28, 2017
- 139
- 289
Dude that's a hell of a trick OoI reveal one secret from my workuse it!
The AI is coded with habit to 'know' everything. When you prompt it: 'woman Britney Spears' it checks memory and found this blonde woman in training data, it found face shape, nose, eyes, body size and shapes, etc. and draw one blond woman looking like this persona. But when you prompt: 'woman Sharaklata Abarubas' is looks at data set and found nothing (such a woman does not exist), then it work on plane B, searching and compering with people with similar name and try to invent race, outlook ,etc. fitting this NAME and finally draw this invented supposed woman. Model use same neuron path to invent this persona everytime (90%+) Then if you like her, save her name and generate images with your own new woman
Thank you!
Photo restoration project. Trained Lora on body details.
PandaRepublic
Member
- May 18, 2018
- 215
- 2,167
PandaRepublic
Member
- May 18, 2018
- 215
- 2,167
Jimwalrus
Well-Known Member
- Sep 15, 2021
- 1,115
- 4,250
Superb consistency, especially the earrings.
i build out a 3 stage image diffusion engine based on SD 2 and use one custom dif model 2 tflite and 1 onnx. i am considering posting the code on github
I'll check out any new GIT, If some one was able to incorporate
You must be registered to see the links
and
You must be registered to see the links
into the web-gui of stable diffusion that would be amazing.
Kass69
Engaged Member
- Jan 10, 2021
- 2,047
- 10,782
- Sep 26, 2018
- 3,137
- 3,216
My Cute Roommate cousin but with tattoo and shorter ponytail
An anime style swordswoman. Took me a while to get it right.
I don't like DALI or Midjourney and SD 1-1.2 leave much to be desired but 2+ works good once you have a well assembled model tamed by reasonable LoRA, a hypernetwork or two and a textual inversion, after that it's just a matter of dialing in the seed and tweeking the prompt. my solution can do very nice video too. i'll link a sample.
You must be registered to see the links
sorry for the rapid edits. theres a link to a sample
Jimwalrus
Well-Known Member
- Sep 15, 2021
- 1,115
- 4,250
Sepheyer
Well-Known Member
- Dec 21, 2020
- 1,611
- 3,865
Thai coastline, isn't it?Awesome clouds and sea!