- Oct 29, 2017
- 812
- 2,191
- Jan 4, 2022
- 239
- 923
- Aug 4, 2020
- 2,567
- 3,306
nnnnnnoooot really, unless you want that specific image....which defeats the point of an ai like this lol
- Dec 21, 2020
- 1,575
- 3,778
Would anyone have suggestions about what settings will produce decent faces in img2img? I can't find the right settings, and the "restore faces=on".
Grrr
You don't have permission to view the spoiler content.
Log in or register now.
You don't have permission to view the spoiler content.
Log in or register now.
Last edited:
- Oct 29, 2017
- 812
- 2,191
If it's a daz model you can move it in daz with different angles, etc. so you can get a minimum of 10 pictures and then make the training with all those pictures.
- Jan 24, 2020
- 1,401
- 3,804
Did you watch any tutorial video? The denoising strength setting is very important. In img2img you focus on this setting rather that sample steps. Sett sample step high enough, above 50 and forget it and focus on cfg scale and denoising strength.
The resolution and ratio is important also. Fit the "red square" to the source image, set "crop and resize". The prompt needs of course describe the source image. Try different samplers, Euler a, Heun or DPM++DSE.
You must be registered to see the links
(img2img timestamp link)If you keep having problems come back for more help.
Last edited:
- Oct 29, 2017
- 812
- 2,191
Practice with one girl at once to see if you can get good results, then try with that picture of two girls.
- Jan 24, 2020
- 1,401
- 3,804
Yes I agree, I think that having two subjects makes it more difficult. It's difficult enough with one subject. Also it's best to use a source image that is "simple", not having too much intricate details such as a control panel with buttons and text etc.
- Dec 21, 2020
- 1,575
- 3,778
fr34ky, Mr-Fox yes, gents, 1 person is no problem, finding the settings is no problem. I was interested if this is me, or if this is the current capability level of the tool - whether it can handle a "real" life scene. My message's context was if anyone found a way to deal with scene-like renderings and change them around. Cool, cool, it seems we may get there soonish, just not yet.
- Oct 29, 2017
- 812
- 2,191
Or inpaint one, send to inpaint the result and inpaint the other
- Jan 24, 2020
- 1,401
- 3,804
My own Tomb Raider project. I wanted to go inverse. A photo into game animation cgi etc.
Img2Img
Source:
Generated:
Then I used the same prompt for Text2Img.
Img2Img
Source:
Generated:
You don't have permission to view the spoiler content.
Log in or register now.
Then I used the same prompt for Text2Img.
You don't have permission to view the spoiler content.
Log in or register now.
- Jan 24, 2020
- 1,401
- 3,804
Not exactly wank material... This was a weird one. I played around with prompt and settings, it came down to trying different measurements, width and height. I have noticed strange behavior with this before. Well I gave it a go...
- Aug 4, 2020
- 2,567
- 3,306
on top of what everyone else suggested I also noticed that negative prompts which counter the positive ones can also make the output better
as in:
say you have "butt" in your positive and nothing in negative and the butt in the image turned out a bit off
you can then put "(butt)" in positives and "butt" in negative and there's a chance it will improve things by quite a bit, for whatever reason
- Aug 4, 2020
- 2,567
- 3,306
- Sep 15, 2021
- 1,054
- 4,040
I've discovered (through the allegedly impossible act of running SD with a 4GB model on my old 2GB GPU) that the model is loaded into system RAM. Provided you've enough of that you should be fine.
16GB should be enough, but 32GB is better and at least it can be expanded unlike vRAM.
- Aug 4, 2020
- 2,567
- 3,306
awesome. I have 16GB of normal RAM so that should be enough but I'll check as well, thx
- Sep 15, 2021
- 1,054
- 4,040
I've been playing around with adding small amounts of LORA embeddings to tweak outfits one way or another rather than adding increasingly excessive weights to prompts "((((low cut))))" etc.
For instance, if your prompts are consistently generating slightly 'disappointing'* outfits:
and you're wanting to spice it up with a rise to the leg line and/or lowering of the neckline, maybe just make it more revealing, why not try seasoning with a pinch of a LORA trained on slingshots?
These are just 0.3 of a LORA that apparently requires a weighting of 2 or more to produce the full 'cheesewire' bikini contest special.
*"Disappointing" is relative of course!
(Prompts and embeddings etc are in the PNG info as usual)
For instance, if your prompts are consistently generating slightly 'disappointing'* outfits:
and you're wanting to spice it up with a rise to the leg line and/or lowering of the neckline, maybe just make it more revealing, why not try seasoning with a pinch of a LORA trained on slingshots?
These are just 0.3 of a LORA that apparently requires a weighting of 2 or more to produce the full 'cheesewire' bikini contest special.
*"Disappointing" is relative of course!
(Prompts and embeddings etc are in the PNG info as usual)
- Dec 21, 2020
- 1,575
- 3,778
"Disappointing outfits". Pfff.