GET3D
inline_tweak
GET3D | inline_tweak | |
---|---|---|
17 | 1 | |
4,124 | 151 | |
0.6% | - | |
4.2 | 8.3 | |
7 months ago | 3 months ago | |
Python | Rust | |
GNU General Public License v3.0 or later | Creative Commons Zero v1.0 Universal |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
GET3D
-
Egregoria is a city simulation with high granularity
Check out: https://github.com/nv-tlabs/GET3D
License looks open. Very demanding hardware requirements (8 A100s).
- Tell HN: The next generation of videogames will be great with midjourney
-
Save money for figure by generate one
With CharTurner it might be possible to extrapolate out a 3D model 🤔 Nvidia was messing with it back in Fall of least year. https://github.com/nv-tlabs/GET3D
-
Creating 3D models using NVIDIA Get3D
Get 3D Code: https://github.com/nv-tlabs/GET3D
-
Ai generated 3d models?
GET3D
- Game development is about to go wild with AI
- Absolutely crazy - addon in blender to add textures to models with text prompts. Dream Textures (SD for Blender) - free addon. My god, it's accelerating at the speed of light.
-
Do you have any tips for converting 2D image to 3D, have you tried asking SD to do various different angles of the same image?
You are going to have a hard time from an SD image as you can't reliably get other angles to build a model, Nvidia's Get3D can try from a single image but the results are basic from what I can make out but I have not run it myself yet : https://github.com/nv-tlabs/GET3D
-
RTX 4090 Launch Thread - Surprise Inside
Honestly: I'm looking into getting a 4090, as someone with a 3090. I really, really push my card doing AI assisted video sequences, machine learning, simulations in blender, production for The largest metaverse convention in the world , and being able to record and stream to AV1 on the fly would be icing on the cake. Though I wish it had 48gb of Vram for custom ML training datasets to use nvidia's nerfs and tlabs Get3d, 24 will do for now. It also pushes through vr pretty well when paired with pci-e 5. Or running renderdoc or anything else. I'm currently working with a small team for an exhibit at Raindance Immersive, and I know the 30+ minutes it takes to generate 30 seconds of footage right now would be easially cut in half for this new show.
-
This room is dynamically generated with GPT-3 creating its person, items and writings, while SD paints the pictures on the wall.
Do you have the resources to run https://github.com/nv-tlabs/GET3D to try to AI generate objects GPT-3 references?
inline_tweak
-
Egregoria is a city simulation with high granularity
I think Rust for games has come really far. I will cite https://arewegameyet.rs/ "Almost. We have the blocks, bring your own glue.".
All the blocks are there and the language is really well suited to games.
On top of my head:
The pros:
- The crate ecosystem and the package manager makes it really easy to integrate any useful component such as pathfinding, spatial partitioning, graphics backend, audio system.. Most crates take a lot of effort to be cross-platform so I can develop on linux and not spend too much time debugging windows releases.
- The strong typing and algebraic data types makes expressing the game state very pleasant. I also found I was able to develop a very big game without too many bugs even though I don't write many tests.
- Ahead of time compilation + LLVM guarantees you won't have to optimise for weird things around a virtual machine. Rust gives you more control to optimise hot loops as you can go low-level.
- I find wgpu to be the perfect balance between ergonomics and power compared to Vulkan. OpenGL support through wgpu is also a nice addition for lower end devices.
- The Rust community is very helpful, you can often talk directly to crate maintainers
The cons:
- Compilation times, when compared to JITed languages such as C# can be very painful. It can be alleviated by buying a 3950X but I still often get 10-30s iteration times.
- The static nature of Rust means you often need a dynamism layer above to tweak stuff that can be awkward to manage. I made inline_tweak for this purpose but it's really far from how easy Unity makes it. https://github.com/Uriopass/inline_tweak
- Since Rust feels very ergonomic, you are tempted to write almost all game logic within it, so mod support feels very backwards to implement as you cannot really tweak "everything" like in Unity games. Thankfully "Systems" game like Factorio or Egregoria can be theoretically split into the "simulation" and the "entities" so mod can still have a great impact. Factorio is built in C++ so has the same problematic. Their Lua API surface is quite insane to be able to hook into everything. https://lua-api.factorio.com/latest/
Now, I have to talk about Bevy: https://bevyengine.org/. It did not exist when I started but it is a revolution in the Rust gamedev space. It is a very powerful 100% Rust game engine that makes you write game code in Rust too. It has incredible energy behind it and I feel like if I'd used Bevy from the start I wouldn't have had to develop many core engine systems. Its modular design is also incredibly pleasant as you can just replace any part you don't like with your own.
What are some alternatives?
stable-dreamfusion - Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
Egregoria - Contemplative society simulation
instant-ngp - Instant neural graphics primitives: lightning fast NeRF and more
bevy - A refreshingly simple data-driven game engine built in Rust
hashcat - World's fastest and most advanced password recovery utility
abstreet - Transportation planning and traffic simulation software for creating cities friendlier to walking, biking, and public transit
magic3d-pytorch - Implementation of Magic3D, Text to 3D content synthesis, in Pytorch
arewegameyet - The repository for https://arewegameyet.rs
stable-diffusion-webui - Stable Diffusion web UI
point-e - Point cloud diffusion for 3D model synthesis
text2mesh - 3D mesh stylization driven by a text input in PyTorch