[Stable Diffusion] Prompt Sharing and Learning Thread

[devilkkw]

I love "install missing custom node function". CUI is literally superior on managing update and extension.
Also finally i've added wildcards tath work like a1111 and i'm really happy for it.
But... i need to know if there are a function to call some data from node:
for example i have a latent image node with 896w and 1152h, is posibble to recall the for example in upscale, and apply multiplier?
Like (latent image w)*2?
I know there are a latent upscale do it, but for test i'm doing a function like this is good, change value manually is pretty boring.

 

[Sepheyer]

I love "install missing custom node function". CUI is literally superior on managing update and extension.
Also finally i've added wildcards tath work like a1111 and i'm really happy for it.
But... i need to know if there are a function to call some data from node:
for example i have a latent image node with 896w and 1152h, is posibble to recall the for example in upscale, and apply multiplier?
Like (latent image w)*2?
I know there are a latent upscale do it, but for test i'm doing a function like this is good, change value manually is pretty boring.

There are math and utility nodes, such as "get size" or somesuch. That's how you grab the dimensions.

 

[Sepheyer]

Another nice comic checkpoint:

You must be registered to see the links

 

[Mr-Fox]

BOOBA!

 

[Mr-Fox]

Seph forgot to mention, it has different styles: Cartoon Style, Semi-realistic, Hard Style, Soft fantasy, Base model .
Pick one and download. The basemodel has trigger words: "Comics style", "Comics", "Cartoon style".
All images were generated with the same prompt and seed, Euler a, 30steps and cgf scale 6.

Cartoon Style	Semi-Realistic	Hard Style	Soft fantasy
Base model "Comics style"	Base model "Comics"	Base model "Cartoon style"	Base model "Comics style, Comics, Cartoon style,"

And bonus.. (hard style)


And extra bonus..

 

[hkennereth]

A new way to fix hands with controlnet.

You must be registered to see the links

ComfyUi Workflow:

You must be registered to see the links

ControlNet Aux:

You must be registered to see the links

Hand Inpaint Model:

You must be registered to see the links

*I have not tried yet.

Took me a little while to get it working due to a bug that was preventing it from working on Windows, but... yeah, it works. Like most things in Stable Diffusion it doesn't reliably work 100% of the time, but when it does work it is pretty transformative.


(I also had my Face Detailer set after the first image, which is why the face also changes)

I found the workflow in the video pretty confusing, but this is pretty much all you need to have in your flow (the red part is just for preview of the masks and controlnet images being generated, but it's not required to make it work):


All in all, I approve, it's now part of my standard workflow. Thanks for the tip!

 

[Mr-Fox]

Another alternative for fixing hands. This was shared by the great Synalon so all credit goes to him for finding this video tutorial.
It's a process very similar to inpainting but it is done with the free image editor krita and ai live painting. Since it's done in an editor you have much more control with the masking process than the rather primitive and simplistic masking you can do with A1111 inpainting. Combining this with ai igeneration looks like it could be a very useful alternative to inpainting with SD and/or after detailer.

You must be registered to see the links

*I have not tried this yet either, it looks promising though.

 

[modine2021]

dont know what's going on. networks quit showing up. jsut that spinning icon. i do have that prompts-all-in-one extension to make up for it. but i still want the normal tabs to work. im annoy they got rid of the red "show extra networks button". and change it to this. nothing but issues since

 

[devilkkw]

stop run a1111,
go to your a1111 folder, see if there are a file called user.css.
if yes, rename it like "old_user.css"
clear browser cache,
restart a1111
check if icon is on.

 

[modine2021]

stop run a1111,
go to your a1111 folder, see if there are a file called user.css.
if yes, rename it like "old_user.css"
clear browser cache,
restart a1111
check if icon is on.

ther was no file by that name. clean out cache though. still same issue. cant figure it out..might go back to 1.6 cause 1.7 gvie nothing but headache since updating.

 

[Sepheyer]

Guys, do you feel like doing a tribute to Jasmine? All submissions welcome.

Spoiler: Prompt

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

 

[devilkkw]

ther was no file by that name. clean out cache though. still same issue. cant figure it out..might go back to 1.6 cause 1.7 gvie nothing but headache since updating.

The issue come also to me with some extension, move the to a backup folder and run without any extension, just for see if cause is some extension. if you have icon back, some extension have not css updated.
Also using browser inspector is good to see error on page and understand what are breaking css.

 

[Mr-Fox]

Guys, do you feel like doing a tribute to Jasmine? All submissions welcome.

View attachment 3244454

eh what kind of "tribute" ?..

Seriously though, could you post your prompt for us that is not into the spagetti monster?

 

[Delambo]

That model was a nice one, thank you Sepheyer and Mr-Fox. Messing with this lora

You must be registered to see the links

 

[Sepheyer]

eh what kind of "tribute" ?.. View attachment 3245135

Seriously though, could you post your prompt for us that is not into the spagetti monster?

I updated the original post with prompt, sorry!

About the tribute - I suddenly caught an obsession bug making me render nothing but Jasmine. Wanted to see what other folks's vision is.

Oh, and by the way, I know what would make Disney's productions less woke.

 

[Mr-Fox]

I updated the original post with prompt, sorry!

wow, I thought for sure you were using a Jasmine lora. Great job. And thanks for sharing the prompt. It's the first time in a long while I took a look at your prompting. I see that some habits remains the same, keeping it simple and very organized. I do aim for the same, though I tend to "bash SD over the head" a bit with mine. Especially when I don't get the result I'm looking for.

PS you forgot to say which ckpt you are using. I suspect it's Pirsius comic style that you linked to but there are many other comic oriented ckpt's it could be also..

 

[Mr-Fox]

PS you forgot to say which ckpt you are using. I suspect it's Pirsius comic style that you linked to but there are many other comic oriented ckpt's it could be also..

 

[Sepheyer]

PS you forgot to say which ckpt you are using. I suspect it's Pirsius comic style that you linked to but there are many other comic oriented ckpt's it could be also..

Indeed, it was Pirsius. I tried a lot of others, a few stood out:

Anime From Hades	Cartoon Realistic	Doomer Boomer	aZovya Artist Tools v4

 

[Krukrufu]

I just started to learn about stable diffusion about a week ago. I have a 1650 card, and it just doesn't work on it, and even when it does, I get plenty of errors, and the restrictions are just too damn much. So I just used the Colab version, and the result was just too damn good. I just wanted to ask if there's any way I can fix few things, as there are some ristrictions on colab's free plan, and i wanted to use controllnet for posing, is there's any way to achive that with image to image?, also are there any lora's for fixing hands .

 

[Mr-Fox]

My sympathies about the card, I know that struggle. You can use controlnet open pose in both txt2img and img2img.
Controlnet also has other useful models such as depth and lineart, they allow you to re-use an image.
Another one is ip adapter, it can use an existing image of a person and then change the pose and clothes and background.
For the hands, yes there are probably loras but it's more common with using embeddings. You can find them on civitai.
Search for either negative or bad hands or similar. Here's a few common ones:

You must be registered to see the links

You must be registered to see the links

Something to consider though, anything meant to correct hands are hit and miss, and any lora or embedding will also affect the image over all not only working on the hands. So is it worth the trade or not? "after detailer" and using its hand model is an alternative I use myself. Yes it will affect the general image slightly but less so I think than the embeddings. Inpainting in img2img tab is a process of masking the hand and with the prompt re-generate that hand, hopefully better this time. Using after detailer with inpainting is a very good way to fix hands. None of these methods can perform miracles though, so if the hands are completely mangled it's less likely to give a good result. I posted just the other day a different alternative using the free image editor "krita" with ai generation. Essentially inpainting inside an image editor.
Since you are hardware limited, I don't know if this is something you can use but I thought I should mention it anyway.
https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-12643242