I am still quite shocked that anyone looked at the side by side images within Nvidia and actually thought this was good and no one would have an issue with this.
Now I will admit that if you don't compare them, the final image looks ok. Like if I did not know what was happening I likely wouldn't give it a second thought. It looks off but so many video games already look off that I don't think I would have really thought anything other than "well it's a video game".
But when compared to the original image it is so obvious that the artistry and the original intent is just completely lost.
They claim that the developers and artists have more control over this, well maybe if that is actually true (because we all know guardrails on AI have been perfect so far...) they should have been involved in using that control for the video showing this off. Otherwise I honestly hope this never ships.
But even if it does, the power requirements for this make it kinda DOA anyways.
lm28469 3 days ago [-]
Gaming isn't even a side project for them anymore, last time I checked it was under 3% of their revenues, I wouldn't be surprised if it's under 1% now, I don't think they care much if at all about this domain anymore
As demoed, it's obviously very bad. But before giving up on it completely, I'd like to see a version that can remain faithful to the original color grading and tone mapping. Those changes affecting the overall look of the whole frame really distract from comparing the more subtle lighting differences where they might be onto something good.
But I'm also skeptical about whether they can pull this off in a way that doesn't exacerbate the already-severe issues DLSS has with latency and temporal stability. Enhancements that make for great screenshots often don't translate to great realtime gameplay.
hbn 3 days ago [-]
An issue I haven’t seen anyone bring up: how are they going to keep the randomly generated sexy new AI face for the characters consistent between shots?
A frame of the character shown 20 hours into the game doesn’t remember the random generated sexy face it gave that character 1 hour into the game.
Everything about this is so stupid.
1 days ago [-]
expedition32 3 days ago [-]
It is really tragic because DLSS has been pretty great so far.
AuthAuth 3 days ago [-]
100ms latency to blur the game isnt what i'd consider great
archagon 2 days ago [-]
In my experience I get 2x perf without visual degradation or any notable latency at all. Certainly not 100ms — I can easily notice 16ms.
AuthAuth 2 days ago [-]
The latency is very noticeable I dont know how you can claim to notice 16ms but not notice that you are getting 80-100ms latency.
archagon 2 days ago [-]
Well, because I'm not getting 80-100ms latency. In a first-person shooter, 100ms would be 6 frames and make the game basically unplayable with a mouse. Also there's nothing intrinsically expensive about DLSS to cause such a latency. I suspect something is wrong with your setup?
AuthAuth 10 hours ago [-]
If you dont believe me you can look up latency tests for it. without DLSS rendering is ~15ms. With preformance mode DLSS that raises to about 30-35MS. Balanced is about 60ms and beautiful is 90-100ms input latency.
zardo 3 days ago [-]
That first image looks great, but will it always deepfake Aubrey Plaza's face onto that character, or will she morph between different actresses?
IronWolve 3 days ago [-]
Might be nice on older games that dont have 4k HD texture packs, or even games like Skyrim or replaying older Witcher 1&2. Its upto the user right? Let people play older games with some better looking gfx. Seems like an easy win, use it or dont use it.
computerdork 2 days ago [-]
Am not 100% what's going on and why everyone is ragging on it, but to me, DLSS 5 clearly improves the graphics most of the time. Yeah, almost all the faces look more real, with more realistic skin and shadows instead looking like those CGI faces with poor detail from 12 years ago.
Personally, think it's just people freaked out that it's being improved on by AI, and therefore apart of the "AI slop" trend. Think if they had done this all with no AI and just polygons, it'd be hailed as a large step forward in graphics.
... and btw, am just as freaked out about AI taking over the creative fields as a lot of others (am a musician myself), but have to try to objective, and in my opinion, DLSS 5 is impressive.
Fizz43 2 days ago [-]
They dont look real the lighting is terrible. There is lighting that would suggest two light sources on one part and lighting that would suggest one light source on other parts. Its jarring.
computerdork 2 days ago [-]
Took another look. You're entitled to your opinion, but, yeah, am not seeing the two light source problem you mentioned, not at least in screenshots I looked at. And for me at least, they look more realistic than with dlss 5 turned off. But may be I'm not seeing something you're seeing.
enragedcacti 2 days ago [-]
The specular highlights on faces definitely look wrong to me though I struggle to describe why. Shadows and diffuse lighting is a totally different story, though. Look at how it completely deletes the shadow of the steeple on the right hand side[1], or how it completely eliminates the shadows on this guy's face and jacket. Overcast lighting is an easy cheat for hyper-realism[3] and almost every single scene shown has softened or absent shadows and more diffuse light.
As an aside, I'm starting to wonder if they are modifying engine settings when switching it on and off. There's clearly some amount of accumulation it has to do and its impossible to frame-by-frame a video of a monitor, but in [1] the first frame snaps from a dynamic shadow of the steeple to a generic small blob shadow, then gets entirely eliminated on the next frame.
Hmm, I do see the shadows being removed in the links you have, and have noticed that the backgrounds do look like their lighted differently from the original, but was wondering if that is just because the AI lights things differently? - they did say that these AI effects are done with the actual 3d assets themselves and is not just some type of filter that run over the existing images, so could see how the lighting could change quite a bit.
Yeah, may be the fact that they are lighted differently from the original is turning people off. Understandable. For me, still find it impressive, and think the level detail in the faces and clothing is a full step up in capability.
enragedcacti 2 days ago [-]
> they did say that these AI effects are done with the actual 3d assets themselves and is not just some type of filter that run over the existing images
That was essentially just Jensen Huang lying during his Q&A. DLSS5 uses the same input data as DLSS<5, which is just screen space color data and motion vectors. From NVIDIAs announcement: "DLSS 5 takes a game’s color and motion vectors for each frame as input, and uses an AI model to infuse the scene with photoreal lighting and materials that are anchored to source 3D content and consistent from frame to frame."
I agree, every shot has something to like, especially in fine details, but I question the feasibility of fixing the issues while running the model on a consumer GPU in realtime. Getting similar improvements without falling back to diffuse lighting would require the model to infer a huge amount of information about off-screen light sources and objects. I'm much more excited about putting my tensor cores and vram towards neural textures since they can actually add detail at the geometry level.
Hmm, actually heard it from a podcast that this is actually working with the 3d assets, and even that statement you quoted says "anchored to source 3D content." Although, that could mean a lot of things and it's still early on, so it could still just be a pass at the end by an AI model. Yeah, I'll stay on the fence until more details are released - and should mention, am no graphics expert, and am only giving my opinion as a fan of good graphics on what the results look like:)
BoredPositron 3 days ago [-]
What's just a sidenote in the slides is that they used two 5090s in the demo video. One for the conventional rendering and one for the AI pass. That's too much overhead for what's achieved. If they both run at 100% it's 1200W mindboggling.
jplusequalt 3 days ago [-]
Don't you know that to game in 2026 you need 40000+ shader cores?
riotnrrd 3 days ago [-]
It's a tech demo.
bigstrat2003 3 days ago [-]
Ok, so it's a tech demo. That doesn't change that it looks bad and uses an unreasonable amount of resources to do its thing. Their tech demo has shown that the tech sucks.
jplusequalt 3 days ago [-]
Does that make it above criticism? It looks uncanny.
I don't like the Netflix CGI slop movie style filter look it gives everything. But that is a more general trend in tv and movies that I just can't stand.
I do think this will eventually be a major part of the graphics pipeline, but I hope it will be limited and masked to things like hair, which is almost impossible to get right in real-time rendering.
sensanaty 3 days ago [-]
She's not even wearing the same clothes lmao. It literally looks like those gooner AI generated fan edits, what the fuck are we doing here guys?
nyxtom 3 days ago [-]
She’s not even wearing the same clothes. This is dumb
misswaterfairy 3 days ago [-]
Controversial opinion.
I am really not a fan of this. Artificially changing graphics to make them 'look better' is similar to my feelings around the (awful) Halo Anniversary remaster.
I thought Halo Anniversary was excellent, but it was a remake and not a remaster. They didn't just upscale the textures or run the game at a higher resolution, they made entirely new graphics assets for it (and music, but the new music didn't have a patch on the original soundtrack).
Narishma 2 days ago [-]
> Controversial opinion.
That is not controversial at all. Everybody is mocking it.
NoPicklez 2 days ago [-]
A controversial opinion would be being a fan of this
Rendered at 12:51:36 GMT+0000 (Coordinated Universal Time) with Vercel.
Now I will admit that if you don't compare them, the final image looks ok. Like if I did not know what was happening I likely wouldn't give it a second thought. It looks off but so many video games already look off that I don't think I would have really thought anything other than "well it's a video game".
But when compared to the original image it is so obvious that the artistry and the original intent is just completely lost.
They claim that the developers and artists have more control over this, well maybe if that is actually true (because we all know guardrails on AI have been perfect so far...) they should have been involved in using that control for the video showing this off. Otherwise I honestly hope this never ships.
But even if it does, the power requirements for this make it kinda DOA anyways.
But I'm also skeptical about whether they can pull this off in a way that doesn't exacerbate the already-severe issues DLSS has with latency and temporal stability. Enhancements that make for great screenshots often don't translate to great realtime gameplay.
A frame of the character shown 20 hours into the game doesn’t remember the random generated sexy face it gave that character 1 hour into the game.
Everything about this is so stupid.
Personally, think it's just people freaked out that it's being improved on by AI, and therefore apart of the "AI slop" trend. Think if they had done this all with no AI and just polygons, it'd be hailed as a large step forward in graphics.
... and btw, am just as freaked out about AI taking over the creative fields as a lot of others (am a musician myself), but have to try to objective, and in my opinion, DLSS 5 is impressive.
As an aside, I'm starting to wonder if they are modifying engine settings when switching it on and off. There's clearly some amount of accumulation it has to do and its impossible to frame-by-frame a video of a monitor, but in [1] the first frame snaps from a dynamic shadow of the steeple to a generic small blob shadow, then gets entirely eliminated on the next frame.
[1] https://youtu.be/4ZlwTtgbgVA?t=435, [2] https://youtu.be/4ZlwTtgbgVA?t=326, [3] Cyberpunk hyper-realism mod: https://www.youtube.com/watch?v=_toA8lErAHg
Yeah, may be the fact that they are lighted differently from the original is turning people off. Understandable. For me, still find it impressive, and think the level detail in the faces and clothing is a full step up in capability.
That was essentially just Jensen Huang lying during his Q&A. DLSS5 uses the same input data as DLSS<5, which is just screen space color data and motion vectors. From NVIDIAs announcement: "DLSS 5 takes a game’s color and motion vectors for each frame as input, and uses an AI model to infuse the scene with photoreal lighting and materials that are anchored to source 3D content and consistent from frame to frame."
I agree, every shot has something to like, especially in fine details, but I question the feasibility of fixing the issues while running the model on a consumer GPU in realtime. Getting similar improvements without falling back to diffuse lighting would require the model to infer a huge amount of information about off-screen light sources and objects. I'm much more excited about putting my tensor cores and vram towards neural textures since they can actually add detail at the geometry level.
https://www.nvidia.com/en-us/geforce/news/dlss5-breakthrough...
I do think this will eventually be a major part of the graphics pipeline, but I hope it will be limited and masked to things like hair, which is almost impossible to get right in real-time rendering.
I am really not a fan of this. Artificially changing graphics to make them 'look better' is similar to my feelings around the (awful) Halo Anniversary remaster.
Summed up nicely by Noodle - https://youtu.be/MyeCb99cb2Q (starts from 2:28)
same take as every other comment
That is not controversial at all. Everybody is mocking it.