Don't know, for example, how AI in animations could work. I spend really much time on the animation process and AI seems handy to me - just telling her: "make a ministry of silly walk" and . bamm! - you get it. But on character creation - the fun part - I think I don't need AI's opinion, really don't care for her aesthetic taste.

May I ask: what's your opinion about AI? Where do you see benefits, where do you see malodourus regarding the future of DAZ studio?

I don’t want to see DAZ Studio disappear from this world. I’ve invested so much into it—so much that it’s probably too much. I don’t want to feel the heartbreak of losing a piece of software I love, and I don’t want to regret the large amount of money I’ve poured into it. That’s why I’m making these proposals.

- a prompting pane inside DAZ studio 2025
- a prompt like "a girl in a bikini sitting on a towel at the beach. she is wearing sunglasses"...
-> creates a new scene
-> loads G9 feminine into the scene and asks what character preset to use showing fitting ones from my library
-> loads a bikini clothting and fits it to the figure again maybe asking which one to use
-> poses and places the figure according to the prompt
-> creates a fitting backdrop/hdri and adjusts the lighting

From there I can further refine, ask studio to check for fitting hair, apply a little wind (and automatically dForce the hair accordingly). If I do not like the bikini texture I can prompt a different color or pattern. Preview and rendering would be possibible either locally or remote.

Of course DAZ marketing could up with some sales ideas. The prompting pane is for free but processing takes place in the cloud. So kind of a token system might be in use providing a certain monthly credit volume for premier users with additional credits to be purchased. Plus DAZ will of course advertise existing products all the time.

That is the only way which makes sense to me. Automize and help through AI but keep the core functionality and let people easily finetune posing or camera angles. 

But DAZ should probably move quick. Flux.1 Kontext is already released and helps folks to keep images consistent whilst doing changes.
 

don

I subscribed to AI just to try it out but I dont think this is a thing for my. I have looked how to cancel it but it doesnt show up in de membership management like it does with DAZ+, DAZ Premier, etc. Where can I find it or doesnt it automatically renew each month? Thanks for telling me.

Will we be able to use one or two photo prompts from rendered images for DAZ AI? Any plans in the works for that? 

Also limitations? Is any nudity allowed. Any combat or monster attacks, such as a vampire bite etc?  

Gotta love the outfit details and the realistic hair.

That said, it's a good thing seeing Daz trying to include AI into the product, since this is clearly the future.

Prompt: "Woman piloting a spacecraft crash lands and is savaged by a house cat."

Seed: 1964012014

Whenever possible I have selected the Victoria 9 character, image dimensions 1024 x 1024. Prompt strictness default. Quality: Balanced. Number of Images: 4, taking the first as the image.

So, let's see the evolution.

13 April 2024

17 April 2024

8 May 2024 (No V9 - I forgot)

9 May 2024:

29 July 2024

8 October 2024:

Regards,

Richard

I want to use AI to enhance the realism of my renders. I was going to install Stable Diffusion, but then I remembered DAZ AI, and as I saw, "Picture to Picture" is on the roadmap.
Is there any information on when this feature will be added, and will it freak out over nudity?

Thinking that perhaps the aborting on its own was deliberate within Daz AI Studio due to censorship, I used a plain-vanilla prompt [shirtless cowboy wearing tight blue jeans] which did not abort but produced this unacceptably amateurish image with facial distortion and an unrealistic depiction of what an actual cowboy would look like in the real world:

Daz AI Studio has very limited value to me if there is in fact censorship built-in. Getting no error messages telling why a rendering aborts on its own is a serious user interface limitation. Can I get any support on correcting this issue. Or can I get my money back?

I would like to share the images from my experiments.

First some blonde princess.

Thank you in advance!

Thank you in advance!

IE, I try to generate an image with the shuttlestar model, and I get some variety of a range rover, I tell it to do teh same with the millenium falcon, and I get a pretty close rendition of what I was hoping for.. with the exception of the image being square... (LOL)

Is this a premium only feature?  am I simply missing how to on the free?  Is it even possible to use store catalog items?

Thanks.

Thank you in advance!

With this tutorial I'll show how I take my daz images like this:

and goto this:

If you're looking to generate consistently high-quality, realistic characters, this is the workflow I use and recommend.

Tools You'll Need

To follow my workflow, you’ll need Automatic1111’s Stable-Diffusion-WebUI. While I had hopes for other platforms like Flux and Forge, they aren’t quite ready for this level of work yet. ComfyUI has potential, but I find it a bit tedious and unstable for my needs. Plus, its inpainting tools haven’t reached the quality required for this workflow (as of my last check several months ago).

System Requirements

You’ll need a powerful GPU with at least 8GB VRAM (ideally 24GB+), but if you’re a long-time DAZ user, I’m betting you already have that covered.

Steps to Get Started

1. Install Automatic1111’s Stable-Diffusion-WebUI

You can follow this YouTube tutorial for detailed installation instructions.

2. Download and Install the Model

For the best results, I recommend using this modified version of SD1.5: EpicPhotogasm.

• At the top of the page, you’ll find different versions. I suggest using Z-Universal (not the inpainting version).
• Download it and place it in your stable-diffusion-webui\models\Stable-diffusion directory.

3. Install ControlNet

Next, you’ll need ControlNet for additional control and detail in your generated images.

1. Install ControlNet from this GitHub repository.
2. Download some useful ControlNet models, such as:
   • IP-Adapter SD1.5/SDXL
   • IP-Adapter FaceID [SD1.5/SDXL]
   • Other modules like Canny and OpenPose are also helpful. You can find them here:
     • For SD1.5: ControlNet-v1.1
     • For SDXL: xinsir ControlNet Models
3. For FacePlusV2 you will also need the Lora. Download from: https://huggingface.co/h94/IP-Adapter-FaceID/blob/main/ip-adapter-faceid-plusv2_sd15_lora.safetensor
   • Once download move it into: \stable-diffusion-webui\models\Lora

Note: The setup can feel a bit messy, but these modules will greatly improve your results.

4. Install Reactor (Optional)

For even more refinement, I highly recommend Reactor. It helps with reshaping faces and other fine details. You can download it from this GitHub repository.

Testing Your Setup

Once you have everything installed, here’s how to test it:

1. Run your WebUI by launching webui-user.bat.
2. In the top-left corner, switch the checkpoint model to the Z-Universal model you downloaded.

Image Generation with Img2Img

1. Switch to the Img2Img tab.
2. Upload the DAZ image you want to modify in the image input section.
3. Configure the following settings:
   • Sampling Method: Use Restart (my recommended method).
   • Schedule Type: Use Automatic (if not available, select Karras).
   • Sampling Steps: Set between 33 and 40.
4. Go to the Resize tab and click the yellow triangle icon to resize your image. If your image is larger than 1440px in width or height, scale it down to that or lower.
5. Set the CFG Scale between 6 and 8 (for now, you can leave it at 7).
6. Denoising Strength is key — start with 0.4 and adjust based on the results.
7. Set the Seed to -1 for random seed generation.

Finally, hit Generate and see what you get!

Some of the results are really close to what I want, exept there are wheels, so itquite frustating... 

I even truied to remove the "without wheel" in my description, in case that would preturb the AI, but I always get wheels:

Do you know how to fix it, please? Doesn't the AI understand negation?

Thank you in advance!

Hello everyone,

Just exploring how AI can be used as one of many tools in the creative process, and settled on 'Kling AI' as the AI generator of choice only due to it's the latest update of this program, v1.6 and got good reviews for the most part. (at time of this post)....and within 'Kling AI' there is another Feature and that is... 'Image to Video'... and I thought this might be interesting.

Could my Daz3D / BeamNG static single images with characters become animated...short answer is yes...although with some caveats.

After uploading my finished artworks to 'Kling AI' my initial reaction after it had finished rendering was 'Holy Moly' this is amazing, seeing your artwork come to life, though only for 5 seconds in this case, but still a great thrill to see this.

However, after experimenting with them for a couple of days, I found that some turned out great while others failed miserably....lol....and while it is amazing to see this, having to wait Hours to even Days before seeing your creation materialize can be time consuming.

My own experience on a couple of occasions, was waiting over 1 day to create some Videos only to find when it did show up, they were unusable...though the time delay was due to high internet usage of Kling AI.

Generally though most of the render times for my 'Image to Video' creations were in the 15mins - 40mins range depending on how much online usage there was.

From what I can see, there's still the usual problem of morphing and distorting of hands and faces, although this could also be that I only had access to the 'Standard' render options in the Menu for my Paid package as the 'Professional Mode' was greyed out, this mode my give much better results, but at a higher cost.
 
Out of the 9 artwork images I uploaded for trial, only 1 turned out very good. (personal opinion)...and that one is 'THE JUDGE, Jury and Executioner', shown below ....really liked the overall movement with minimal / no distortion and Kling AI also did a good job of following the prompt I wrote for this one which was....

'Female slowly looking behind at burning vehicle behind her'.

...or you can just drop your image in, have no prompt and see what happens

Although in my prompt I did not mention add movement to the fire flames 'Kling AI' automatically did this, top marks in this one.

Thought this and other Videos are a great addition to my static screenshot artwork, the story behind 'The Judge' could be....

'Female cyborg Soldier poses for photo after succeeding in her mission to distroy the enemy (which is my Artwork screenshot)...then once photo has been taken,...'At ease Soldier'..., then she looks behind her'....as seen in the animated GIF Video....this blew my mind...lol

Below is the static BeamNG Screenshot that I created.

Below is what 'Kling AI' gave me with the above screenshot uploaded for conversion.

At the end of the day AI is here to stay, so why not use it as one of the many tools in the creative journey.

While the results look great, there's something far more fulfilling about creating one's own artwork from scratch within BeamNG and Daz3D to achieve the Screenshot images I personally envisage.