AI [AI Art] - Show Us Your AI Skill *NO TEENS*

[KingBel]

If you render DAZ, why you need SD then?
DAZ characters is so ugly and with wrong proportions can guess G8 character/face from first look.

I just like the control in DAZ... but I am quite new to SD, so there may be a better way.. I was just trying to think of solutions based on my current skillset.

 

[Mr-Fox]

If you render DAZ, why you need SD then?
DAZ characters is so ugly and with wrong proportions can guess G8 character/face from first look.

G9 is changing all that. Daz3d is getting much better. But it's still not like the best stuff SD can generate.

 

[MoeMoeGames]

My original pictures are from Honey Select 2 by the way.

 

[Elefy]

One is from DAZ for my client , another is SD inpaint. Spot the difference

 

[azrazr]

 

[fr34ky]

I haven't tested this out myself yet, but if you can train a checkpoint (or Lora as Elefy said) of your custom character (created in DAZ for example), you could then create consistent gens with that character. This Youtube video explains the process:

You must be registered to see the links

.

Seems like it would work. I am gonna do a test with one of the game characters that I normally do fanart for (possibly Ann from Big Brother) and see what the results look like.

Seems like someone might have done that already

 

[Rknudson]

Odd question but can you make a realistic dick on any of the male models you use? I thought it worked at one point but now I'm getting some kind of hybrid with the female antatomy. Not sure if it's just the program or I corrupted something with a model I installed.

 

[fr34ky]

Odd question but can you make a realistic dick on any of the male models you use? I thought it worked at one point but now I'm getting some kind of hybrid with the female antatomy. Not sure if it's just the program or I corrupted something with a model I installed.

I created some sex images and worked ok, but it's hard to make any kind of genitals, be aware of your negative prompts if you are getting some weird hybrids.

 

[Trasher2018]

Nice .. today just started with this ...

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: 0cc0ee1bcb4c24a8c9715f66cede06601bfc00c8
Traceback (most recent call last):
  File "D:\stable-diffusion\stable-diffusion-webui\launch.py", line 360, in <module>
    prepare_environment()
  File "D:\stable-diffusion\stable-diffusion-webui\launch.py", line 272, in prepare_environment
    run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
  File "D:\stable-diffusion\stable-diffusion-webui\launch.py", line 129, in run_python
    return run(f'"{python}" -c "{code}"', desc, errdesc)
  File "D:\stable-diffusion\stable-diffusion-webui\launch.py", line 105, in run
    raise RuntimeError(message)
RuntimeError: Error running command.
Command: "D:\stable-diffusion\stable-diffusion-webui\venv\Scripts\python.exe" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'"
Error code: 1
stdout: <empty>
stderr: Traceback (most recent call last):
  File "<string>", line 1, in <module>
AssertionError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check

but ..

>>> torch.cuda.is_available()
True
>>> torch.cuda.device_count()
1
>>> torch.cuda.current_device()
0
>>> torch.cuda.get_device_name(0)
'NVIDIA GeForce RTX 4070 Ti'
>>>

Has someone an idea how to solve that? ... and no, not using cuda is not an option ^^

 

[atheran]

 

[Mr-Fox]

View attachment 2430337

Beautiful image. Would you mind sharing wich checkpoint you are using and prompt etc?

 

[atheran]

Beautiful image. Would you mind sharing wich checkpoint you are using and prompt etc?

There you go.

Spoiler: Stuffs

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

The base is from civitai Deliberate's showcase, and I changed the prompts a little.

Then I took it to Photoshop and DxO Filmpack for some more realistic look of a photo.

 

[Mr-Fox]

It's gorgeous. I'm always looking for tools and ways to improve the quality or create different looks.
DxO is it a plugin or extension?

I have seen "ENSD:31337" in many generation data's and I'm curious what it is. Do you know?

 

[atheran]

It's gorgeous. I'm always looking for tools and ways to improve the quality or create different looks.
DxO is it a plugin or extension?

I have seen "ENSD:31337" in many generation data's and I'm curious what it is. Do you know?

You must be registered to see the links

That sums it up pretty nicely, better than if I tried to explain it

 

[Microtom]

 

[azrazr]

 

[DreamingAway]

Has someone an idea how to solve that? ... and no, not using cuda is not an option ^^

Are you using xformers?
You might need to downgrade pytorch to a previous version or maybe update your Drivers?

I don't see anything specific about NVIDIA GeForce RTX 4070 Ti that would cause this issue - you should be fine, could also try " --precision full --no-half " - in case your GPU doesn't like fp16.. but I think 4070 should..

 

[tdree]

 

[DreamingAway]

With Control Nets and LORA..
I think we are at the point where most of the obvious flaws of AI can be mitigated / removed.

I'm waiting for the slew of Adult games to be created now.. Get to work!

:Cracks Whip:

 

[KingBel]

Was playing around with the Latent Couple extension to find a way to better manage the properties of multiple characters in a gen. It works quite well, and once you have the models situated properly within the regions you specified in Latent Couple, you can change multiple properties without having the 'bleed' that always occurs with trying to add prompts to multiple character gens.

An example: