[Stable Diffusion] Prompt Sharing and Learning Thread

[Sepheyer]

Load it into PNG Info...

View attachment 2509166

Whoa, the thread is becoming so popular even Borat wondered in. Hi its nice. Very nice.

 

[Jimwalrus]

Well.

Following on from SR7 having a LoRA made of his work,

You must be registered to see the links

LoRA exists now...

Just a few quick and dirty tests:

 

[Sepheyer]

Well.

Following on from SR7 having a LoRA made of his work,

You must be registered to see the links

LoRA exists now...

Just a few quick and dirty tests:
View attachment 2509386 View attachment 2509387

Ohh, fuck yea!

 

[Jimwalrus]

Ohh, fuck yea!

I'm sure those with more experience of anime etc. will be able to do a lot better than me with this - I generally go for photorealism.

 

[modine2021]

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]

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).

 

[modine2021]

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

@ 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

 

[Jimwalrus]

@ 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

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).

 

[miaouxtoo]

Does civitai helper take a while to load for you guys? I had to remove the extension because something was clogging up my automatic1111

 

[modine2021]

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).

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

 

[sharlotte]

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:
   
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: I don't need to select a 'processor' as I've already done the work in openpose.
5. type your prompts and generate
   
6. get these:

The other way I use is to just get to txt to img:

1. 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: using these prompts:
   
2. You can change the preprocessor and model, use same prompts and you get different results, here with 'hed' instead

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.

 

[sharlotte]

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:

You can upload all the png thumbnails I inserted in your PNG INFO tab to see the prompts and various details.

 

[Jimwalrus]

Does civitai helper take a while to load for you guys? I had to remove the extension because something was clogging up my automatic1111

Interesting. Not had that issue myself, but I always ensure I've got the latest version.

 

[modine2021]

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: View attachment 2511457
   
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: View attachment 2511459 I don't need to select a 'processor' as I've already done the work in openpose.
5. type your prompts and generate View attachment 2511462
   
6. get these: View attachment 2511463 View attachment 2511464 View attachment 2511465

The other way I use is to just get to txt to img:

1. View attachment 2511466 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: View attachment 2511468 View attachment 2511469 View attachment 2511471 using these prompts: View attachment 2511473
   
2. You can change the preprocessor and model, use same prompts and you get different results, here with 'hed' instead View attachment 2511476 View attachment 2511477 View attachment 2511478

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.

finally got it acting right. took 50/11 times. but it now remembers the pose from the image. still need a bit practice( the feet wrong in this one)

original pic




OpenPose pic

 

[sharlotte]

Yeah, practice makes perfect! Vary the prompts, the preprocessor types and models and you will get different results, it's all a steep learning curve.

 

[devilkkw]

have some of you nice suggestion on Textuail inversion?
i experimented a lot on these day, and i see many tutorial, but every tutorial use same "learning rate", and so i experimented with it.

On my test seem work great on high value, i mean i train on 1200 step and get good result with value like "1.05, 3.2,2.1"
Have someone experienced it?

 

[sharlotte]

I read in different TI on CIVITAI people using 0.004 or 0.005 and AI Entrepreneur uses the following '0.05:10,0.02:20,0.01:60,0.005:200,0.002:500,0.001:3000,0.005' - I have not yet successfully completed on. Just starting it and seeing over 4-5 hours of training was a bit deflating...

 

[Mr-Fox]

have some of you nice suggestion on Textuail inversion?
i experimented a lot on these day, and i see many tutorial, but every tutorial use same "learning rate", and so i experimented with it.

On my test seem work great on high value, i mean i train on 1200 step and get good result with value like "1.05, 3.2,2.1"
Have someone experienced it?

I have not tried out making my own TI. When I tried TI's by other's they only created problems for me such as taking over too much and breaking the prompt etc, even at low weight. And after I removed them they tend to linger.
So atm they are cancer in my view. But disregarding all that, when I made my Lora I found that slow learning was the ticket.
I have no idea if it transfers to TI's.

 

[devilkkw]

I read in different TI on CIVITAI people using 0.004 or 0.005 and AI Entrepreneur uses the following '0.05:10,0.02:20,0.01:60,0.005:200,0.002:500,0.001:3000,0.005' - I have not yet successfully completed on. Just starting it and seeing over 4-5 hours of training was a bit deflating...

Wow, is high time. at 3000 step my train run in 30 mins.
Then in 1200 step i run it in 14 mins.
Can you prepare your image for train?

I have not tried out making my own TI. When I tried TI's by other's they only created problems for me such as taking over too much and breaking the prompt etc, even at low weight. And after I removed them they tend to linger.
So atm they are cancer in my view. But disregarding all that, when I made my Lora I found that slow learning was the ticket.
I have no idea if it transfers to TI's.

Yes, i decide to trin my own because many on downloaded are really messed up, seem bad initialization word or too many step.
I'm testing now actually i reach good result from 3 to 14 cfg.
Also is not powered like LORA, is possible to training lora on 6Gb?

 

[Mr-Fox]

Here's some rentry's I found on this subject.

You must be registered to see the links

You must be registered to see the links

You must be registered to see the links