AvatarCLIP
MotionDiffuse
AvatarCLIP | MotionDiffuse | |
---|---|---|
4 | 1 | |
1,040 | 784 | |
- | - | |
0.0 | 10.0 | |
about 1 year ago | about 1 year ago | |
Python | Python | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
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.
AvatarCLIP
- Half way in my AA college career and just started my electives. Need help
-
[R] Text to 3D characters + expression editing + pose generation
Based on similar works CLIPActor and AvatarCLIP the codebase implements similar pipeline using mesh and differentiable rasterization to provide a spedeup allowing for ~10 min character generation on a weak Google Colab GPU
- "AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars", Hong et al 2022 (crosspost of another user's post)
- "AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars", Hong et al 2022
MotionDiffuse
-
[R] MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model + Gradio Demo
github: https://github.com/mingyuan-zhang/MotionDiffuse
What are some alternatives?
CIPS-3D - 3D-aware GANs based on NeRF (arXiv).
StableVideo - [ICCV 2023] StableVideo: Text-driven Consistency-aware Diffusion Video Editing
multinerf - A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF
text-to-motion - Official implementation for "Generating Diverse and Natural 3D Human Motions from Texts (CVPR2022)."
giraffe - This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"
text2room - Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).
Make-It-3D - [ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
stable-dreamfusion - Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
MotionGPT - [NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs