UniVRM
UniVRM is a gltf-based VRM format implementation for Unity. English is here https://vrm.dev/en/ . 日本語 はこちら https://vrm.dev/ (by vrm-c)
OpenSeeFace
Robust realtime face and facial landmark tracking on CPU with Unity integration (by emilianavt)
Our great sponsors
| UniVRM | OpenSeeFace | |
|---|---|---|
| 39 | 7 | |
| 2,449 | 1,312 | |
| 2.9% | - | |
| 9.4 | 4.2 | |
| 29 days ago | 3 months ago | |
| C# | Python | |
| MIT License | BSD 2-clause "Simplified" License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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.
UniVRM
Posts with mentions or reviews of UniVRM.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-06-12.
- How do you guys make UniVrm work?
-
Help with VRM model?
https://github.com/vrm-c/UniVRM this is what I used for exporting to vrm files but I usually export them as vsf files https://github.com/emilianavt/VSeeFaceSDK
- New to the idea of vtubing but not sure if I want to invest too much
-
When the Mistlands suddenly open up and you can see. It truly is the most beautiful biome Valheim has
The model was purchased from FancyWhippet ( https://fancywhippet.gumroad.com/l/DEER ), but any Unity character model that has been rigged for VR should work. Just load it in to Unity version 2020.3.33 (the version Valheim is currently running on), add the VRM for Unity tool ( https://github.com/vrm-c/UniVRM ) to the project, and then use that tool to export the model to VRM. That's what I had to do as FancyWhippet provides Unity Project files.
-
Can't add HANA Tools and VRM Converter into Unity at the same time.
go here https://github.com/vrm-c/UniVRM/releases/tag/v0.108.0
-
Unity VRM Export - MATERIALS_CONTAINS_NULL
Try asking here: https://github.com/vrm-c/UniVRM/issues
- A bit more from my project :)
- would anyone be willing to help me make this into a 3d object to attach to my vroid model I've been trying for months and have made no progress on this its driving me crazy and I wanna make my vtuber debut so bad but I cant without this since its super important to the lore of my character thank you
-
I made random eye movements
Actually, I'm not very good at animation either, so I just created a script that randomly moves the target that the eyes are following. The processing itself is handled by UniVRM. Here is an example:
- My own avatar
OpenSeeFace
Posts with mentions or reviews of OpenSeeFace.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-04-07.
-
Getting face feature pose statistics
I got something working modifying OpenSeeFace and it's an option and I might try to rewrite it in something compiled, but I'd like to look at the other options first.
-
This may be a silly question but can I hire someone to make me a customized avatar for vr chat?
Lastly, face tracking is either built in or uses a plugin device. You would also use OSC to manipulate blendshapes. I'd take a look at Opens Face.
-
Any recommendations for VTuber setup on Linux? Ideally something that's completely open source.
Th best/only options I found were basically the old standby of Wine running closed source applications. Even then the end result was rather incomplete... because may of the best tracking options are simply closed source. (Note: Vseeface does offer an open source library)
- Running OpenSeeFace on Linux with python 3.10
-
Open map with gaze tracking for someone with paralysis
There are only a few libraries that come to mind but take a bit of work to get started. MediaPipe Unity Plugin has eye tracking with a whole lot of types of tracking(head, hands, body). OpenSeeFace has models that do head and eye tracking. This repo uses Unity's neural net inference library, Barracuda, to run a MediaPipe iris landmark model (I haven't personally tested this library). Not sure how to translate eye landmarks to the position a player is looking at in a screen though. Hopefully this list of libraries gets you on the right path!
-
I'm going to try to use VSeeFace again, is there a way to change how lip syncing works?
OpenSeeFace is open source. If you are using it with VSeeFace, you can just replace the Binary folder with your own build.
-
I'm making a renderer for facetracking data
It uses OpenSeeFace for facetracking and engine patches/vrm code from the V-Sekai team.
What are some alternatives?
When comparing UniVRM and OpenSeeFace you can also consider the following projects:
openseeface-gd - A GUI for running OpenSeeFace.
AssetStudio - AssetStudio is a tool for exploring, extracting and exporting assets and assetbundles.
kalidokit - Blendshape and kinematics calculator for Mediapipe/Tensorflow.js Face, Eyes, Pose, and Finger tracking models.
avatars - Avatar system for Exokit
vpuppr - VTuber application made with Godot 4
GLTFUtility - Simple GLTF importer for Unity
VTuber_Unity - Use Unity 3D character and Python deep learning algorithms to stream as a VTuber!
UnityGLTF - Runtime glTF 2.0 Loader for Unity3D
fastT5 - ⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
ml-agents - The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
transformer-deploy - Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀