[Stable Diffusion] Prompt Sharing and Learning Thread

Mr-Fox

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,794
sharlotte said:
Unpredictable but delicious and pleasing to the eye! I had read on it but never tried it before.

I had an issue where I created monsters (Cthullhu would have run for the subaquatic hills) with double of everything, legs over body, really awful stuff. I went carefully over every slider, options, and it turns out I was generating my picture with too many pixels mostly in the height dept... Anything over 1154 pixels in height just could not cope with the models I was using.

As part of this small fact finding mission, I started using the 'realistic vision 2.0' from civitai. Great results, far less monstrosities, defects than before. A few samples as png so prompts included. I did not use any hires on these.
View attachment 2506648 View attachment 2506649 View attachment 2506650 View attachment 2506651 View attachment 2506652 View attachment 2506655 View attachment 2506657 View attachment 2506658 View attachment 2506661 View attachment 2506660 View attachment 2506661 View attachment 2506665 View attachment 2506666 View attachment 2506664
Click to expand...
That's not specific to wich model you are using. SD in general can't deal with large sample resolution, this is an universal limitation and it has also to do with how everything has to be trained atm. Try to stay below 1024px for both axis. Higher resolution has to come from either Highres fix or upscaling. Atm upscaling is a worse alternative and I honestly doesn't expect this to ever change. We can only hope for better native support of higher resolutions and also improved Highres fix.
Of course some checkpoints will give better result than others. I have not used realistic vision much but everything I have seen about it looks great.
You must be registered to see the links
is otherwise an obvious option but it's of course part of the fun to try out different things.
Other ones to try out is
You must be registered to see the links
and
You must be registered to see the links
. Both has inpaint checkpoints and Deliberate has a few other
You must be registered to see the links
as well.
Imo clarity is superior to both however it doesn't have an inpaint merge afaik.
 
  • Like
  • Red Heart
Reactions: sharlotte, Jimwalrus and Sepheyer
Sepheyer

Sepheyer

Well-Known Member
Dec 21, 2020
1,531
3,618
Mr-Fox said:
That's not specific to wich model you are using. SD in general can't deal with large sample resolution, this is an universal limitation and it has also to do with how everything has to be trained atm. Try to stay below 1024px for both axis. Higher resolution has to come from either Highres fix or upscaling. Atm upscaling is a worse alternative and I honestly doesn't expect this to ever change. We can only hope for better native support of higher resolutions and also improved Highres fix.
Of course some checkpoints will give better result than others. I have not used realistic vision much but everything I have seen about it looks great.
You must be registered to see the links
is otherwise an obvious option but it's of course part of the fun to try out different things.
Other ones to try out is
You must be registered to see the links
and
You must be registered to see the links
. Both has inpaint checkpoints and Deliberate has a few other
You must be registered to see the links
as well.
Imo clarity is superior to both however it doesn't have an inpaint merge afaik.
Click to expand...
Also, from using composing workflow in CUI on 1344x768 images, it seems the sampler plays a large role. Heun constantly produces either twins or fused bodies. DPMPP_SDE/Kerras is the most robust, pretty much spot on 100% of the time - reliably produces one woman whereever you put her. Euler A is 80% spot on, 20% WTF.

Yea... Heun is like the dude who can never settle. But lotsa bad fuses too.

a_00171_.png
You don't have permission to view the spoiler content. Log in or register now.
 
  • Like
  • Haha
Reactions: Pogo123, sharlotte, Jimwalrus and 1 other person
Jimwalrus

Jimwalrus

Active Member
Sep 15, 2021
931
3,423
KoutaruArts said:
Anyone got the Amber Heard Lora From Civitai??, the author either got banned or delete big part of hes content if some does please share it.
Click to expand...
It was actually a Textual Inversion, albeit a .bin file rather than a .pt

Just as a disclaimer, I can vouch that I personally have had no issues with the .bin file in the attached RAR, but am not responsible for any loss or damages etc. You're downloading a .bin file from a dodgy online forum, from some rando with a non-existent woman as his avatar!
I've also included the last version of the Civitai.info file in case you have the Civitai Helper extension (if you don't, I can highly recommend it!) View attachment AmberHeardTI.rar
 
  • Haha
  • Like
Reactions: Mr-Fox, VanMortis and Sepheyer
S

shellie2000

New Member
Jun 23, 2021
2
4
sharlotte said:
Unpredictable but delicious and pleasing to the eye! I had read on it but never tried it before.

I had an issue where I created monsters (Cthullhu would have run for the subaquatic hills) with double of everything, legs over body, really awful stuff. I went carefully over every slider, options, and it turns out I was generating my picture with too many pixels mostly in the height dept... Anything over 1154 pixels in height just could not cope with the models I was using.

As part of this small fact finding mission, I started using the 'realistic vision 2.0' from civitai. Great results, far less monstrosities, defects than before. A few samples as png so prompts included. I did not use any hires on these.
View attachment 2506648 View attachment 2506649 View attachment 2506650 View attachment 2506651 View attachment 2506652 View attachment 2506655 View attachment 2506657 View attachment 2506658 View attachment 2506661 View attachment 2506660 View attachment 2506661 View attachment 2506665 View attachment 2506666 View attachment 2506664
Click to expand...
Hi Its Nice, Share me the prompts
 
  • Haha
Reactions: sharlotte
M

modine2021

Member
May 20, 2021
381
1,255
ugh... tried to make a pose using reference images.. i used this tutorial
You must be registered to see the links
followed the exact process. its pretty simple. but get nothing. always get either a different pose or the character is a tangle of arms and legs and ass. any you good with ControlNet? time for a simple tutorial?
 
sharlotte

sharlotte

Member
Jan 10, 2019
268
1,440
You have quite a few training videos:
You must be registered to see the links

You must be registered to see the links

Loads more out there. These are clear, step by step (incl installing) so you can't really go wrong (well you can, but you learn from it).
 
  • Like
  • Love
Reactions: Sepheyer and modine2021
M

modine2021

Member
May 20, 2021
381
1,255
Jimwalrus said:
It was actually a Textual Inversion, albeit a .bin file rather than a .pt

Just as a disclaimer, I can vouch that I personally have had no issues with the .bin file in the attached RAR, but am not responsible for any loss or damages etc. You're downloading a .bin file from a dodgy online forum, from some rando with a non-existent woman as his avatar!
I've also included the last version of the Civitai.info file in case you have the Civitai Helper extension (if you don't, I can highly recommend it!) View attachment 2508905
Click to expand...
@ Civitai Helper ...... excllent extention. my only gripe is that it doesn't delete/replace the old version of the model. so you end up with 2 versions
 
  • Like
Reactions: Mr-Fox and Jimwalrus
Jimwalrus

Jimwalrus

Active Member
Sep 15, 2021
931
3,423
modine2021 said:
@ Civitai Helper ...... excllent extention. my only gripe is that it doesn't delete/replace the old version of the model. so you end up with 2 versions
Click to expand...
TBH, I actually prefer it that way - sometimes the previous version of a model has its uses (especially running tests and recreating / modifying older images).
 
  • Like
Reactions: Mr-Fox and modine2021
miaouxtoo

miaouxtoo

Newbie
Mar 11, 2023
46
132
Does civitai helper take a while to load for you guys? I had to remove the extension because something was clogging up my automatic1111
 
M

modine2021

Member
May 20, 2021
381
1,255
sharlotte said:
You have quite a few training videos:
You must be registered to see the links

You must be registered to see the links

Loads more out there. These are clear, step by step (incl installing) so you can't really go wrong (well you can, but you learn from it).
Click to expand...
thanks. but unfforuantly none cover what im looking for. im tryin to use a psoe from an reference image. im using OpenPose Editor "detect from an image" . then sending it to Controlnet then clicking generate. but the tuts i find only cover manually posing
 
Last edited:
sharlotte

sharlotte

Member
Jan 10, 2019
268
1,440
No probs, this is the way I do it - there must be better ways, but it works for what I do.
  1. select a jpg
  2. add it to your openpose if that's what you want and detect from image as per this screenshot: 1.JPG
  3. once finished, I just save it as png somewhere on my PC
  4. I go to txt to image and then I open control net, import the png I just created and select 'openpose' as per this: 2.JPG I don't need to select a 'processor' as I've already done the work in openpose.
  5. type your prompts and generate 3.JPG
  6. get these: 00003-2063450916.png 00004-2063450917.png 00005-2063450918.png

The other way I use is to just get to txt to img:
  1. 4.JPG attach the image you want to work with directly in the controlnet section, select your preprocessor and model. With this image and 'depth' I get these results: 00009-1279159727.png 00010-1279159728.png 00011-1279159729.png using these prompts: 5.JPG
  2. You can change the preprocessor and model, use same prompts and you get different results, here with 'hed' instead 00012-4015750513.png 00013-4015750514.png 00014-4015750515.png

Hope this helps. Others may have more tips and tricks, but this works fine for me at the moment.
I use realistic vision 2.0 (
You must be registered to see the links
) as a model.
 
  • Like
  • Love
  • Red Heart
Reactions: sebas395, sbasrin, Mr-Fox and 5 others
sharlotte

sharlotte

Member
Jan 10, 2019
268
1,440
I changed the prompt slightly to a 'white South African' and change the hair colour with the 'hed' preproc and model in controlnet, same photo as above for starting point. Here are the results: 00019-1339891430.png 00022-1871515314.png 00029-3001256330.png 00026-3680200866.png

You can upload all the png thumbnails I inserted in your PNG INFO tab to see the prompts and various details.
 
  • Like
  • Love
Reactions: modine2021, Mr-Fox, VanMortis and 1 other person
Jimwalrus

Jimwalrus

Active Member
Sep 15, 2021
931
3,423
miaouxtoo said:
Does civitai helper take a while to load for you guys? I had to remove the extension because something was clogging up my automatic1111
Click to expand...
Interesting. Not had that issue myself, but I always ensure I've got the latest version.
 
You must log in or register to reply here.
Top Bottom