Lists (2)
Stars
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
Efficient Part-level 3D Object Generation via Dual Volume Packing
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
Official implementation of "Text-Aware Image Restoration with Diffusion Models"
A collection of procedural geometry nodes tools developed by CGVIRUS studio
Offsets the timeline left/right with custom shortcuts
Use your phone as a 6DOF controller for Blender
The official code implementation of the paper "OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data."
*CREPE+HYBRID TRAINING* A very experimental fork of the Retrieval-based-Voice-Conversion-WebUI repo that incorporates a variety of other f0 methods, along with a hybrid f0 nanmedian method.
Python script that slices audio with silence detection
Copy Shapekeys allows you to copy the shapkeys (with animation) from one mesh to another
A Native Multimodal LLM for 3D Generation and Understanding
Abandoned fork, use Jiggle Physics: https://github.com/naelstrof/blender-jiggle-physics
A Blender addon that uses Google's Mediapipe Face Landmarker to map facial expressions onto a 3D character in real time.
Gamepad addon for Blender. Control active camera using d-pad or analog movement.
Blender add-on to get 3D mesh visualization using hand gesture in real time.
PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
[SIGGRAGH'25] Official repository of LayerFlow: A Unified Model for Layer-aware Video Generation
Any-to-Bokeh is a novel one-step video bokeh framework that converts arbitrary input videos into temporally coherent, depth-aware bokeh effects.
Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
Official repo for paper "Sparse Representation and Construction for High-Resolution 3D Shapes Modeling".
deepbeepmeep / Wan2GP
Forked from Wan-Video/Wan2.1Wan 2.1 for the GPU Poor
Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment
Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
Blender: Driving Animation with Sound ( incuding driver-manager )