The maanHimself repository appears to be 35 hours older than the aloshdenny one based on `created_at` from the GitHub API. maanHimself's `pushed_at` predates aloshdenny's `created_at` too.
That doesn't guarantee maanHimself is the original author, but it's looking likely.
If they take Neural Rendering far enough, they can get rid of those useless raster and RT cores completely and ship compute and tensor cores only on all their chips
Rasters are far too good for simple textures + simple geometry. Even the best neural rendering works better when it has the bones of geometry, motion and depth to work with.
Even in a "neural rendering optimistic" future, I can't see a way in which traditional rendering doesn't survive as a "control channel" that informs what the neural rendering does. To do otherwise would require making the bulk of the game logic neural too.
This. This is what they are trying to do. If they can flip the entertainment industry to use neural rendering using their "proprietary" api's then they would have cornered a market from the bottom.
But I thought Nvidia “loves open source” (they don’t) and they are now a supporter for open source and open weight models by acquiring Huggingface? (They don’t actually care)
But the line is drawn when it involves CUDA and any part of their closed source compilers (nvcc).
There are obvious reasons why they are closed source, but it’s becoming pointless since Deepseek have open sourced their AI compiler and compute libraries with DeepGEMM and eventually they will catch up.
I'm rather surprised that it doesn't take the z-buffer as an input. I would have thought that would have provided useful information, it's one of the more useful forms of contolnet.
The official one seems to do, as well as other info from the engine (I think remember their mentioning LOD/UV map hints in one of the public demos, or articles, a few months back--or it might have been an Unreal Engine podcast)
> The inference interface uses the engine-rendered RGB image as a dense, registered observation of visible scene appearance. It provides dense, pixel-aligned evidence for object support, occlusion boundaries, composition, and local material properties; engine motion vectors separately provide temporal correspondence.
> Existing image generative models commonly rely on text embeddings, exemplar images, or spatial control fields such as depth, edges, segmentation, and pose [...] These conditions are effective for general-purpose generation and editing, but they do not uniquely determine the object identities, materials, visibility relationships, lighting decisions, and pixel-aligned detail contained in an engine-rendered frame. DLSS 5 is therefore conditioned on the rendered frame itself.
I think this is mainly so it can use the existing hooks for DLSS upscaling without requiring changes to the renderer, AMD is working on a comparable method which uses adapter networks to slot normals and material properties from the renderer into the diffusion model: https://gpuopen.com/learn/temporally-stable-generative-illum...
Even relatively small RGB -> depth models are pretty good. Which kind of implies depth is well encoded in the RGB, and adding depth would not really reduce entropy, while costing bandwidth.
Given that you bring the weights from NVIDIA's DLSS. So basically, the repo contains reverse engineered machinery that produces the exact same output given the same model.
Yes, see the numbers below. In most games, it's basically unusable if you want to play on 60 FPS or above unless you have a 5090.
The current implementation is more of a tech demo than a practical way to play games (+ officially it's available in 1 game). It's _fast enough_ to make some impressive YouTube videos but you most likely won't want to play anything with it yet.
Nvidia has stated that they're still working on improving the performance. No doubt future hardware generations will also include further hardware optimisations.
The potential for this kind of technology is pretty awesome, especially given that people have also found ways to add this to emulators.
I really hope they do, but the market for gaming cards is looking mighty bleak right about now. 5090 is up over 80% since November last I checked and my 5080 is up 50%.
NVIDIA removing all mentions of gaming in their financials doesn’t bode well either, and from a fiduciary standpoint it would be negligent to sacrifice any capacity for higher-margin AI chips to make gaming cards.
Again, I hope I’m wrong and we see new cards summer/autumn 2027, but I would not bet my savings on it.
Modders have added the ability to use the upscaler after DLSS 5, personally I don't know how sound this method is but the quality is pretty good, and allows to play games with DLSS 5 at 4k 60FPS with something that is not a 5090.
Worth remembering it is running a single-step diffusion model working in pixel space to generate each frame, it's a technical feat in itself that people are even using the words "frames per second"
RTX 5070, 9.6 ms with NR of Optiscaler in Stalker 2. It's payable and I enjoy new visual. Especially shadows and faces are incredibly detailed and precise. Landscapes not so much.
Am I the only one who feels a sense of disinterest in a project where the main README is LLM-generated? Does the author not have time to write what they did and how it's used?
Agree. But I feel like there's merit to having an open source implementation of anything, no matter who/what wrote it. I'm just hoping the results are validated well.
I'm more upset about it being factually wrong, e.g. both mentions of "git-ignored" are absurd (why would you mention it if it's not in the repo?) and wrong (they are in the repo).
I notice this, that AI likes to write about things that are not in there. Like i review AI generated output, notice unnecessary things, and asks AI to remove that. So AI removes that and adds that "this and that, that was used or described like this, was removed because bla bla bla" to the document.
I think its somehow needs to talk (write) about the things that are in the context and removal is there so AI predicts that it should be there.
Yeah, I call it bugfix storytelling. Once upon a time this class far far away had this red hooded method...
Especially egregious if both adding and removing the thing happens in one commit. Git should be telling the story, and if it can't then there _is_ no story!
"Am I the only one who feels a sense of disinterest in a project where the code is LLM-generated? Does the author not have time to code the project?"
This is how I feel about every single project announcement on HN recently, they are already bragging about models all over the place, why shouldn't they go full way down being replaced by the Borg?
If the README is >90% AI generated and it is as long as a novel, I am not going to read it and will assume that the author did not read or write it either.
Unfortunately it is slop, beyond the comprehension of the author unless they are experienced with DLSS internals to explain it in depth.
I assume this is meant to run with the weights people extracted from the latest NBA game, where it was first trialled.
> Isn't the mote that Nvidia has is they work with studios to generate the training data from the game, then they ship a model per game?
That was true for the very first version of DLSS, from DLSS 2 on the models have been universal - the per-game adjustments are done on the inference end by changing the effect intensity or masking out objects
They used to ship one model per game but now there is a single model, however they still do minor updates to it presumably to fine-tune it on new games
It used to be in dlss1. I think it's completely been put to pasture now though, it's way too much work and can't really cover some of the main things people actually want to use dlss5 on, for instance Morrowind.
> It takes one rendered frame (a low dynamic range proxy of it, three lanes of Gaussian noise, the previous frame's output reprojected, and five conditioning scalars) and produces four f32 channels per pixel: an RGB residual and one temporal-blend logit.
> The temporal path is implemented, but in the demo: the network's history input lanes and its per-pixel blend logit drive a reprojected feedback loop (docs/frame.md). The dlss5vk tool runs single frames with no history, which is what the reference captures were made with.
From this I assume the network uses the (via motion vectors) reprojected previous frame in order to increase temporal stability, i.e. similarity over adjacent frames. But this isn't strictly necessary, and apart from it, DLSS 5 is a pure post-process filter. So you could apply it to an old animated CGI movie like Final Fantasy (2001) [1]. Which should make it look significantly more realistic, at the cost of some flicker or other temporal instability.
One could also apply it to still images, like old renders from Tomb Raider [2], where temporal stability is not a factor. The difference to conventional text-to-image models with a "make it photorealistic" prompt would be that DLSS 5 strongly adheres to the underlying geometry.
https://github.com/aloshdenny/open-dlss
That doesn't guarantee maanHimself is the original author, but it's looking likely.
Copyright (c) 2026 maan
So... Either alooshdenny stole the commits, or it's an alias for maan.
just unsure who's original ))
Programmer: OpenDLSS...
Jensen : Wait. Not like that! (╯°□°）╯︵┻━┻
Even in a "neural rendering optimistic" future, I can't see a way in which traditional rendering doesn't survive as a "control channel" that informs what the neural rendering does. To do otherwise would require making the bulk of the game logic neural too.
But the line is drawn when it involves CUDA and any part of their closed source compilers (nvcc).
There are obvious reasons why they are closed source, but it’s becoming pointless since Deepseek have open sourced their AI compiler and compute libraries with DeepGEMM and eventually they will catch up.
At least their support helps the open-weight ecosystem.
They care when the agendas align, and they don't when they won't.
> The inference interface uses the engine-rendered RGB image as a dense, registered observation of visible scene appearance. It provides dense, pixel-aligned evidence for object support, occlusion boundaries, composition, and local material properties; engine motion vectors separately provide temporal correspondence.
> Existing image generative models commonly rely on text embeddings, exemplar images, or spatial control fields such as depth, edges, segmentation, and pose [...] These conditions are effective for general-purpose generation and editing, but they do not uniquely determine the object identities, materials, visibility relationships, lighting decisions, and pixel-aligned detail contained in an engine-rendered frame. DLSS 5 is therefore conditioned on the rendered frame itself.
What kind of sorcery is this ? Very impressive work !
Nowadays it takes one well written prompt to a frontier LLM to produce something like this.
LLMs are really good at deobfuscating or even decompiling code.
The current implementation is more of a tech demo than a practical way to play games (+ officially it's available in 1 game). It's _fast enough_ to make some impressive YouTube videos but you most likely won't want to play anything with it yet.
Nvidia has stated that they're still working on improving the performance. No doubt future hardware generations will also include further hardware optimisations.
The potential for this kind of technology is pretty awesome, especially given that people have also found ways to add this to emulators.
Again, I hope I’m wrong and we see new cards summer/autumn 2027, but I would not bet my savings on it.
RTX 5060: 9.9 ms at 1080p
RTX 5070: 10.2 ms at 1440p
RTX 5080: 13.7 ms at 2160p
RTX 5090: 8.2 ms at 2160p
Source: https://www.youtube.com/watch?v=3EfLjmdG29Q&t=600
I think its somehow needs to talk (write) about the things that are in the context and removal is there so AI predicts that it should be there.
AI probably should not be writing docs, commit logs or comments.
Especially egregious if both adding and removing the thing happens in one commit. Git should be telling the story, and if it can't then there _is_ no story!
bold of you to assume the code wasn't llm generated as well.
This is how I feel about every single project announcement on HN recently, they are already bragging about models all over the place, why shouldn't they go full way down being replaced by the Borg?
Unfortunately it is slop, beyond the comprehension of the author unless they are experienced with DLSS internals to explain it in depth.
Isn't the mote that Nvidia has is they work with studios to generate the training data from the game, then they ship a model per game?
Or is my knowledge outdated here and they're just using a single generalised model?
> Isn't the mote that Nvidia has is they work with studios to generate the training data from the game, then they ship a model per game?
That was true for the very first version of DLSS, from DLSS 2 on the models have been universal - the per-game adjustments are done on the inference end by changing the effect intensity or masking out objects
They have a technical report on the neural rendering part of DLSS 5 which goes into it: https://research.nvidia.com/labs/adlr/files/DLSS5_Report.pdf
They don't. Only DLSS 1 was trained specifically per each game.
there's no way that's true!?
> The temporal path is implemented, but in the demo: the network's history input lanes and its per-pixel blend logit drive a reprojected feedback loop (docs/frame.md). The dlss5vk tool runs single frames with no history, which is what the reference captures were made with.
From this I assume the network uses the (via motion vectors) reprojected previous frame in order to increase temporal stability, i.e. similarity over adjacent frames. But this isn't strictly necessary, and apart from it, DLSS 5 is a pure post-process filter. So you could apply it to an old animated CGI movie like Final Fantasy (2001) [1]. Which should make it look significantly more realistic, at the cost of some flicker or other temporal instability.
One could also apply it to still images, like old renders from Tomb Raider [2], where temporal stability is not a factor. The difference to conventional text-to-image models with a "make it photorealistic" prompt would be that DLSS 5 strongly adheres to the underlying geometry.
1: https://www.imdb.com/title/tt0173840/
2: https://www.tombraiderchronicles.com/images/artwork-high-res...