So for whom is this tool for?

Mada

Padone said:

Ivy said:

.. Ai generated by where the prompts follow a storyboard or story script ..

That's exactly the weak point of AI and why it's not useful, I mean at all. In a story, even for static backgrounds, you need various different views of the same environment, from different camera angles. Now AI can't do that, it can't "remember" a scene and give you different shots of it. The same as AI can't do different shots of the same character, eventually interacting with other characters and the scene.

Its rapidly reaching the stage where it can do that, and also where loras would be useful in training the AI to create different shots from the same environment. Using the same character is also a lot closer, for example the AI is trained to use Michael and Victoria right now so you can definitely get consistency across images.

Mada

FSMCDesigns said:

AI would be helpful in this aspect, but not as an image generator, but as an enhancer, something DAZ should implement with their AI progran since it would be more beneficial to a community that creates renders. 

Might not be that far away :) but first step is getting the AI up and running and out there, finetuning it to users' needs etc. I think future enhancements will make current Daz Studio users more excited about AI - and without replacing DS - instead making it part of a very useful creative workflow. 

linvanchene

My thoughts after one week of experimenting with Daz AI Studio:

 

Separate applications for two different usage cases

AI tools can be used to enhance existing 3D software like Daz 3D Studio.

3D tools can be used to enhance AI Image Generators like Daz AI Studio.

I think it is great that there are separate software applications with a dedicated UI for two different approaches to create images.

Both have their advantages and disadvantages.

 

Daz3D is in the position to provide unique solutions based on Daz Studio for AI Image Generators

• a Pupeteer plugin for Daz AI Studio to adjust character poses in a 2D interface as ControlNet input
• a realtime 3D viewport for Daz AI Studio to pose a Genesis figure to adjust character poses as ControlNet input
• a real time 3D viewport for Daz AI Studio with a depth map shader to translate, rotate and scale 3D scenes as ControlNet input
• img2img for style transfer (announced for Daz AI Studio on about page)
• inpainting (announced for Daz AI Studio on about page)
• Face Transfer as a post-processing effect applied after image generation

3rd party solutions for those tasks do exist for local offline versions of Stable Diffusion.

Unfortunately, they cannot all be used for commercial purposes. Continued support and development is not guaranteed.

Daz could provide reliable long-term solutions.

 

Image quality & style

I am happy with the image quality of the current Daz AI Studio checkpoint for some types of images (sci-fi, vehicles, toon).

I had some luck with generating attractive characters without using the Victoria and Michael LoRA.

I found the results of the Michael LoRA interesting but was not happy with the look of Victoria.

Subjective taste, the uncanny valley...

I miss the ability to blend shapes or reduce the morph strength as in Daz 3D Studio.

An option to combine the LoRA of Michael and Victoria with other Stable Diffusion XL checkpoints to create different styles could be interesting.

 

All-purpose vs specialized checkpoints

I do wonder what will happen to the current checkpoint if it is further trained in different areas.

A prompt that in one specific area yields great results may create different results after further training with other images.

How often will there be training updates for one all-purpose checkpoint by Daz?

Would multiple specialised Daz checkpoints for different themes like fantasy, scifi etc. yield better results?

It might be useful to have access to past versions of checkpoints for long-term projects that rely on generating the same look of images.

 

bohemian3

This tool was definately made for me. 

In Beta it is really impressive so far - once they add the other features, more characters, and the tool evolves I see that it could be a major player in the AI image generation space.  I've been using it already to create Michael 9 images to 'train' MidJourney - much quicker than having to do renders.  Consistent characters in MidJourney is a real challenge and already DAZ AI Studio does it better.  I have some examples in my DAZ Gallery using Michael 9 in MidJourney with multiple characters (I like the photorealism of that generator for my ascetic.)  

Congrats to the dev team on the Beta - I really see the potential!

Padone

Mada said:

Padone said:

Ivy said:

.. Ai generated by where the prompts follow a storyboard or story script ..

That's exactly the weak point of AI and why it's not useful, I mean at all. In a story, even for static backgrounds, you need various different views of the same environment, from different camera angles. Now AI can't do that, it can't "remember" a scene and give you different shots of it. The same as AI can't do different shots of the same character, eventually interacting with other characters and the scene.

Its rapidly reaching the stage where it can do that, and also where loras would be useful in training the AI to create different shots from the same environment. Using the same character is also a lot closer, for example the AI is trained to use Michael and Victoria right now so you can definitely get consistency across images.

That would be phenomenal. If the AI can allow to "save definitions" of characters and environments for later use, then understand the "director language" for the camera and lights and figure poses, then we can reach a point where manually doing it in a 3D app is no more necessary. But honestly, I'm not as optimistic as you that this is any close. Actually AI is only good to generate single images not related by any context, that makes AI completely unuseful for storytelling.