[Stable Diffusion] Prompt Sharing and Learning Thread

[me3]

Do anyone have any experience or ideas for ways to make SD NOT replace the face and instead purely "improve"/detail the existing one?
While i wasn't exactly prompting for it, the face that showed up fit very well, problem is that with almost any detailing/denoising it starts being replaced with a far more human and "pretty" face. Even at just 0.1 denoising it's the first ting that gets replaced. Prompt, seed, etc is all the same through out and there's no "face restore/detailing" used.

 

[Synalon]

Do anyone have any experience or ideas for ways to make SD NOT replace the face and instead purely "improve"/detail the existing one?
While i wasn't exactly prompting for it, the face that showed up fit very well, problem is that with almost any detailing/denoising it starts being replaced with a far more human and "pretty" face. Even at just 0.1 denoising it's the first ting that gets replaced. Prompt, seed, etc is all the same through out and there's no "face restore/detailing" used.
View attachment 3442884

Maybe turn off restore face and use an extension that sharpens the image, that may be all you need.

 

[devilkkw]

Oh well, the generation speed is a turtle, something wrong with the optimization
Deleing venv did not help
Any idea how to fix it?

All was working just fine like 3 weeks ago (30-60 sec at max for generating 1 pc)
And now it's slow as hell

View attachment 3432030
View attachment 3432051
View attachment 3432054
View attachment 3432056
View attachment 3432069
View attachment 3432058

What's about driver version?
Read

You must be registered to see the links

for switch fallback function memory added in nvidia driver.

 

[hkennereth]

Do anyone have any experience or ideas for ways to make SD NOT replace the face and instead purely "improve"/detail the existing one?
While i wasn't exactly prompting for it, the face that showed up fit very well, problem is that with almost any detailing/denoising it starts being replaced with a far more human and "pretty" face. Even at just 0.1 denoising it's the first ting that gets replaced. Prompt, seed, etc is all the same through out and there's no "face restore/detailing" used.
View attachment 3442884

At 0.1 denoise the image should barely change at all, nevermind replace the face; if this was happening with an upscaler it wouldn't even look upscaled since the denoise is too low. I'd say that there's probably something else going on there, but with the amount of information provided I can't really hazard any guesses as to what.

 

[Mr-Fox]

I was able to play decently with Stable-Diffusion with an AMD RX 5700XT (about 2 - 3.2 it/s, 512*512), but on linux (Ubuntu 22.04 with torch 1.13.1+rocm5.2 for compatibility). The only problem is that every image generated the memory of the PC is filled more and more until the desktop stops responding, forcing a restart (I have 32GB).

Is there any option to free memory?

Which Ui are you using? I would recommend Forge. It has a better memory management than A1111, it will clear the memory as a part of the generation process, especially before upscaling.

You must be registered to see the links

Tutorial:

You must be registered to see the links

 

[LongJohn77]

Which Ui are you using? I would recommend Forge. It has a better memory management than A1111, it will clear the memory as a part of the generation process, especially before upscaling.

You must be registered to see the links

Tutorial:

You must be registered to see the links

Thanks for the advice, I had read about Forge a few days ago but I have not tried yet.

 

[g900vroot]

So I followed the instructions and installed A1111 per the instructions in the OP... thank you for that!

Generated a bunch of images, but nothing just was really coming together well, and then blammo. Wow, can I marry this one?



Per the rules, the prompts are attached in the image, drop it in your PNG Info for details.

Thanks for turning me onto this software. My poor 3060Ti is getting a workout now.

 

[Sharinel]

So I followed the instructions and installed A1111 per the instructions in the OP... thank you for that!

Generated a bunch of images, but nothing just was really coming together well, and then blammo. Wow, can I marry this one?

View attachment 3456705

Per the rules, the prompts are attached in the image, drop it in your PNG Info for details.

Thanks for turning me onto this software. My poor 3060Ti is getting a workout now.

Ouchy mama, that negative prompt. You're running an XL checkpoint so 99.9% of that stuff isn't needed - I would keep it at " EasyNegative,ng_deepnegative_v1_75t " and get rid of the rest of War and Peace you have in there. Here's my own version with no negative prompts, slightly tweaked prompt parts (no EE breasts, doesn't work. I substituted 'huge') and slightly different cfg scale/steps as I dont use the lightning variant of Juggernaut (same seed)



And the same seed/data using different checkpoints - Proteus v0.3, Dreamshaper8XL and Prony2.5

Spoiler

You don't have permission to view the spoiler content. Log in or register now.

 

[g900vroot]

Ouchy mama, that negative prompt. You're running an XL checkpoint so 99.9% of that stuff isn't needed - I would keep it at " EasyNegative,ng_deepnegative_v1_75t " and get rid of the rest of War and Peace you have in there. Here's my own version with no negative prompts, slightly tweaked prompt parts (no EE breasts, doesn't work. I substituted 'huge') and slightly different cfg scale/steps as I dont use the lightning variant of Juggernaut (same seed)

Yep, that's part of stuff I'm still learning.... much of that was copied from posts way back in the early days of this thread.... and I still haven't quite figured out some of the positive components.... trying to get larger than "B" cup breasts seems to be a challenge, for example... thus why I had "EE".

Also just discovered I didn't have the Tensor optimizations installed, so I'm working on that part right now.

Learning. Thank you for the constructive comments!

 

[Sharinel]

Yep, that's part of stuff I'm still learning.... much of that was copied from posts way back in the early days of this thread.... and I still haven't quite figured out some of the positive components.... trying to get larger than "B" cup breasts seems to be a challenge, for example... thus why I had "EE".

Also just discovered I didn't have the Tensor optimizations installed, so I'm working on that part right now.

Learning. Thank you for the constructive comments!

What I still do is trawl through the images in Civitai, 99% of them have the prompts used to make them. If you are using a particular checkpoint, go look at it's civitai page, scroll down until you see the pics that were made with that checkpoint and open some to see what prompts/negative prompts/steps/cfg are used and which bits you are interested in to liberate for your own prompts (it's not called stealing, no sirree Bob...)

 

[felldude]

You must be registered to see the links

 

[DD3DD]

different checkpoints - Proteus v0.3, Dreamshaper8XL

Are WOW!

 

[felldude]

Working with a custom lora (Mostly using XL now but still SD for a few things)
This image caught my eye thought it would be a good game poster or something. (I added the text in Gimp and XL kept it even at 0.5)

 

[Sepheyer]

Working with a custom lora (Mostly using XL now but still SD for a few things)
This image caught my eye thought it would be a good game poster or something. (I added the text in Gimp and XL kept it even at 0.5)

Please can you add the source png file with the prompt?

 

[felldude]

Please can you add the source png file with the prompt?

Without the lora it looks like this

 

[Sepheyer]

Without the lora it looks like this

Please can you update the original post with a png file that contains the prompt? This is the requirement of the thread. Otherwise the post becomes AI Art suitable for the AI Art thread.

 

[felldude]

Please can you update the original post with a png file that contains the prompt? This is the requirement of the thread. Otherwise the post becomes AI Art suitable for the AI Art thread.

As the OP your welcome to delete either but as for the content and the name of the thread I learned that XL can retain Text you add and do image to image on even at 0.5

But your not going to be able to recreate the image without the source image, and the lora when I am posting an Image to Image

Also you could add the png header to an image just by runing at .01....I pointed this out for the Civitai contest also

 

[BlenderGuy]

Can someone help me out? I can't have a Black Bull with a vagina! It's not a good look at all!

I stated large penis in the prompt and ended up with this.

 

[Sharinel]

Can someone help me out? I can't have a Black Bull with a vagina! It's not a good look at all!

I stated large penis in the prompt and ended up with this.

View attachment 3497889

I've had this a few times, and it's mainly been because the model/checkpoint hasn't been trained with NSFW stuff (hence why you see the NSFW tag in the title of a lot of models on Civitai). Check by keeping the prompt and seed the same but use a NSFW model and see if it shows then? You could try using

You must be registered to see the links

to compensate if you'd rather keep using the model you have, but if you are going to produce NSFW stuff you are better using a checkpoint designed for it.

 

[BlenderGuy]

I've had this a few times, and it's mainly been because the model/checkpoint hasn't been trained with NSFW stuff (hence why you see the NSFW tag in the title of a lot of models on Civitai). Check by keeping the prompt and seed the same but use a NSFW model and see if it shows then? You could try using

You must be registered to see the links

to compensate if you'd rather keep using the model you have, but if you are going to produce NSFW stuff you are better using a checkpoint designed for it.

And there we go! Cheers! Life saver. Will now devote 1000 sleepless hours to playing with one!