Log in
Register

VaM 1.x DLSS 5 in VAM2 + DLSS 5 Experiments in VAM1

Threads regarding the original VaM 1.x
PEREGRINEEEEEEEEEEEE said:
Why are all the screenshots with DLSS5 being removed from the media section?

I don't know if the people posting them are deleting them, but that doesn't seem to be the case...
Click to expand...

Because AI enhanced screenshots cannot be hosted. That's written in the TOS and policies have been updated recently especially for NR shots.
 
Phew, even without VR it looks damn realistic... using CuddleMocap's scenes and it is another world (at least for me).

I don't want to play a mum of 2 who cosplays Cloud when playing FF7 (that was a comment on the "Cloud gone wrong" NR images :D), but damn, the subtle better lighting makes it already so interesting. Really looking forward where technology will bring us in some years.

NR2.jpg
 
Going to have to check this out. VAM 1.0 might have a bit more life in her after all.
 
julianfx said:
Did you have any luck yet with getting VR to work?
Click to expand...
Man, you’re expecting something pretty quickly that is actually quite difficult to do properly. DLSS 5 is a lot more complicated than it looks. Right now we don’t have proper engine-level integration. For full control you need the SDK and an actual connection to the scene itself. Semantic masking can automatically separate different types of objects, while engine-level masking lets developers or artists explicitly tell the renderer where and how neural rendering should be applied. VR without that foundation is basically impossible to do properly. I wouldn’t expect a well-working VR implementation anytime soon.

I can expand a little on what I meant because I’ve looked into the technology more closely now.
For example those weird faces people show in anime-style games don’t mean the technology is somehow “destroying creativity.” Without proper integration, the model is simply running without the artistic controls it’s supposed to have basically following the default behavior it was trained and configured for. And after looking through the SDK this is really the important part: the artist decides what can be changed, where it can be changed and how strongly. There are controls for structure andtone, semantic masking, engine-level masking and local intensity masks/textures. So DLSS 5 doesn’t take creative freedom away. With proper integration, the final control still stays with the creator.

For example, if I look at a glass cup in my scene and think it looks bad, I can tell the neural renderer that this particular object should be heavily reworked into more natural-looking glass, while leaving the other objects untouched or only changing them very slightly. And in VaM right now we basically don’t have that foundation yet. Getting neural rendering to run is one thing but properly controlling it at the scene and individual object level is a completely different problem
 
EvilBox said:
Man, you’re expecting something pretty quickly that is actually quite difficult to do properly. DLSS 5 is a lot more complicated than it looks. Right now we don’t have proper engine-level integration. For full control you need the SDK and an actual connection to the scene itself. Semantic masking can automatically separate different types of objects, while engine-level masking lets developers or artists explicitly tell the renderer where and how neural rendering should be applied. VR without that foundation is basically impossible to do properly. I wouldn’t expect a well-working VR implementation anytime soon.

I can expand a little on what I meant because I’ve looked into the technology more closely now.
For example those weird faces people show in anime-style games don’t mean the technology is somehow “destroying creativity.” Without proper integration, the model is simply running without the artistic controls it’s supposed to have basically following the default behavior it was trained and configured for. And after looking through the SDK this is really the important part: the artist decides what can be changed, where it can be changed and how strongly. There are controls for structure andtone, semantic masking, engine-level masking and local intensity masks/textures. So DLSS 5 doesn’t take creative freedom away. With proper integration, the final control still stays with the creator.

For example, if I look at a glass cup in my scene and think it looks bad, I can tell the neural renderer that this particular object should be heavily reworked into more natural-looking glass, while leaving the other objects untouched or only changing them very slightly. And in VaM right now we basically don’t have that foundation yet. Getting neural rendering to run is one thing but properly controlling it at the scene and individual object level is a completely different problem
Click to expand...

He asked for a reminder on that topic and we are aware that it would not be fully implementated yet but to play around with would be nice.
 
hazmhox said:
Because AI enhanced screenshots cannot be hosted. That's written in the TOS and policies have been updated recently especially for NR shots.
Click to expand...
hi. what idea is behind such policies? now as AI is build in VAM (i know that do not offcialy but lets take thing as they are in real life) so screens are realy get directly from application and no "outer apps" enhance them.
 
rabbit1qaz said:
hi. what idea is behind such policies? now as AI is build in VAM (i know that do not offcialy but lets take thing as they are in real life) so screens are realy get directly from application and no "outer apps" enhance them.
Click to expand...

  1. It is not built in.
  2. It still "won't be built in" (so to say) even with an official DLSS release implemented in VAM 2, as 50xx gen covers around 6% of the market at the moment which makes this unfaithful to what you get ingame without that type of GPU
  3. it's a broad "AI screenshot enhancement" policy, which was mainly about external tools ( simple reshade enhancements being included in that )
  4. First and foremost, this whole "enhancement forbidden" (which was driven by AI in the first place) is to protect people from abuse and scams for content not reflecting the product you could pay for (as the hub contains link to paid content)

For now, DLSS enhanced shots have a specific gallery category they should go in. And that's it.
Your releases should reflect content that would work "as is" without the need of external tools, mods or specific hardware.
 
Note: you are free to mod however you want your VAM to display the final image however you wish. But the hub needs to reflect as much as possible what the app can output.
 
33fps single person atom, so yeah, pretty big FPS hit. 75fps with it turned off. To be clear, my VR is set to limit it that way. I am on a 5090 with a 9800x3D.
 
Last edited:
I did a 3 female person atom scene with DLSS 5 on in VR, works, averages around 18FPS (jumping between 16-22.)
 
Hey everyone. Recently, we removed some posts from this thread that included links to various 3rd party repos and download sites. We discussed this as a team, and decided that some links should be allowed -- github, nvidia, discord, etc.
We still won't allow links to direct file downloads such as mega, google drive, etc -- if you have a tool you want to share (such as Bepinex) please point your link to the official download page rather than trying to host the file yourself.

I will be restoring some of the posts we removed over the weekend that included external links.
 
You must log in or register to reply here.

Similar threads

E
VaM 1.x When will VAM2 be Ready to do stuff like in the VAM1?
Replies
1
Views
2K
hazmhox
hazmhox
H
Is possible this quality in VAM (or VAM2)?
Replies
7
Views
8K
spidaman75
S
B
Any plans for a 1.x update to implement DLSS / FSR support?
Replies
7
Views
7K
AWWalker
AWWalker
H
My UIAssist buttons for better experience in VR
Replies
17
Views
6K
vamp3003
V
M
Where the heck is VAM2?
Replies
2
Views
3K
maximumVR
M
Back
Top Bottom