[Stable Diffusion] Prompt Sharing and Learning Thread

[fr34ky]

Oh man that sucks. I use it all the time, it's great. I run comparisons very often to weed out the best settings, wich sampler to use and many other scenarios. For instance I made several different iterations of my Lora that I could compare with the same prompt and seed thanks to plot script. I have never had any error specific to this. If nothing else works a simple re-install will likely fix it.

The error I get is AssertionError: VAE from function argument doesn't exist: auto

I have 2 other installations of SD and the error happens in all of them.

I used it in the past for some tests, but after this problem happened and it drained my brain energy I stopped caring.

 

[devilkkw]

Try this link .

You must be registered to see the links

Thank you, this is a test with your lora from 0.1 to 0.8 with simply prompt

Spoiler: simply prompt text

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

For me best value is 0.6, so try added some photographic trigger at these value. This is the result.


If it is your first lora, wow man, you rule!!

 

[fr34ky]

Oh man that sucks. I use it all the time, it's great. I run comparisons very often to weed out the best settings, wich sampler to use and many other scenarios. For instance I made several different iterations of my Lora that I could compare with the same prompt and seed thanks to plot script. I have never had any error specific to this. If nothing else works a simple re-install will likely fix it.

I can't confirm 100% but after some tries I could use x/y/z without problems, so I just set the z in 'nothing'.

Kind of weird, but if it works who cares, I hope it reminds like that.

 

[Mr-Fox]

Thank you, this is a test with your lora from 0.1 to 0.8 with simply prompt

Spoiler: simply prompt text

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

For me best value is 0.6, so try added some photographic trigger at these value. This is the result.
View attachment 2499646

If it is your first lora, wow man, you rule!!

Thank you very much. I'm pretty happy with it myself.
Try add "vivid light". You can scale it back if it's too much, "(vivid light:0.6)".

 

[fr34ky]

Any idea of what is the limit for words on the prompts? I'm searching about that and there is no clear answer, but there is something about 150 or 75 tokens and I've seen some long ass prompts that won't fit in anyway into that limit.

 

[Mr-Fox]

Any idea of what is the limit for words on the prompts? I'm searching about that and there is no clear answer, but there is something about 150 or 75 tokens and I've seen some long ass prompts that won't fit in anyway into that limit.

There isn't a limit but it is divided into groups of 75. This is the explaination I have seen. "A token is a sequence of characters that represents a single unit of meaning in a text. It is a fundamental concept in NLP, as most NLP models operate on a token level, meaning they process text one token at a time".

(NLP: Natural language processing in artificial intelligence ).

 

[Mr-Fox]

Come to bed..

Spoiler:

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

Yup, hands are still a big problem for SD. I hope this area improves rapidly.

 

[Sepheyer]

Spoiler: CUI Prompt

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

 

[Mr-Fox]

View attachment 2504321

Spoiler: CUI Prompt

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

Wow. That's one of your best yet.

 

[Jimwalrus]

Not sure if this has already been covered or not, but there is an extension in WebUI (Embedding Inspector) to allow weighted merging of embeddings, models etc.
It seems to be a great way to create very consistent characters for, ooh, let's say, GAMES without it being obvious that the character is just a merge of two celebs...

For instance, I merged my TIs of

You must be registered to see the links

and

You must be registered to see the links

at 0.5 each to create an entirely new embedding (I just called it SK1NNY, for fairly obvious reasons).

One part Kylie:

and one part Zoe Voss:

gives this young lady:


The influence of both is fairly clear, but only when you know the two source embeddings.

I ran some more of her as checks for consistency and they turned out pretty well.

Spoiler: More

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

 

[Jimwalrus]

Not sure if this has already been covered or not, but there is an extension in WebUI (Embedding Inspector) to allow weighted merging of embeddings, models etc.
It seems to be a great way to create very consistent characters for, ooh, let's say, GAMES without it being obvious that the character is just a merge of two celebs...

For instance, I merged my TIs of

You must be registered to see the links

and

You must be registered to see the links

at 0.5 each to create an entirely new embedding (I just called it SK1NNY, for fairly obvious reasons).

One part Kylie:
View attachment 2506528
and one part Zoe Voss:
View attachment 2506529
gives this young lady:
View attachment 2506527

The influence of both is fairly clear, but only when you know the two source embeddings.

I ran some more of her as checks for consistency and they turned out pretty well.

Spoiler: More

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

Further findings.
It's not exactly predictable. It doesn't appear to be "taking a pinch of celeb A and a pinch of celeb B", it seems to just be a largely random, but consistent, merge. Also, if one embedding is strong, it can overpower the other.

For instance, this is

You must be registered to see the links

merged with

You must be registered to see the links

each at 0.5 multiplier:

Pretty much Cameron Diaz. It is a very strong embedding.

Changing the weighting to 0 multiplier for Cameron and 0.4 for Kylie produced a bit of a surprise:

As you can see, internally consistent but unpredictable. The afro came from nowhere!

I shall continue my research into producing pictures of random attractive women by mashing together two unrelated celebrities...

Next thing to check will be how it compares to in-prompt mixing of embeddings i.e. "KYL13M:0.5:C4M3R0ND14Z:0.5:1"

EDIT: Also, yay 1000 posts on this thread!

 

[sharlotte]

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.

 

[KoutaruArts]

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.

 

[Mr-Fox]

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

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.

 

[Sepheyer]

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.

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.

Spoiler: More

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

 

[miaouxtoo]

I've been using chatgpt to generate prompts for some of these. I wanted one boy, one girl walking up a hill wearing stylish clothing.

Nope. Nope. Doh.

 

[sharlotte]

As chief Lone Watie would say: 'endeavour to persevere!'

 

[Jimwalrus]

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.

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

 

[shellie2000]

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

Hi Its Nice, Share me the prompts

 

[Mr-Fox]

Hi Its Nice, Share me the prompts

Load it into PNG Info...