TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
-
Updated
Dec 21, 2025 - Python
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
rCM: SOTA Diffusion Distillation & Few-Step Video Generation based on sCM/MeanFlow
ICCV 2025-CTMSR:Consistency Trajectory Matching for One-Step Generative Super-Resolution
Full-dose Whole-body PET Synthesis from Low-dose PET using Consistency Model
Speculative branching cache engine with optimistic versioned commits. Inspired by MVCC, OCC and local-first architectures. Includes design doc, testing strategy, benchmarks and HTTP API.
Add a description, image, and links to the consistency-model topic page so that developers can more easily learn about it.
To associate your repository with the consistency-model topic, visit your repo's landing page and select "manage topics."