Kandinsky 5.0: A family of diffusion models for Video & Image generation
- diffusion
- distillation
- kandinsky
- text-to-video
142,187 visible repositories in the index
1–6 of 6 · Most stars
Kandinsky 5.0: A family of diffusion models for Video & Image generation
rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale
SparkDiffusion: Accelerating DiT video generation by 265× via joint Sparsity, Distillation, Quantization, etc.
EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.
On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
A general framework for distilling human-created multimodal resources into reusable, executable skills that AI agents can browse, compose, and run, validated across diverse domains including web, PowerPoint, Excel, Blender, CAD, Unreal Engine 5, and REAPER-based music production.