HyperFlow H3 Flash: Video Rebirth's 13.7B, 4- to 8-step compressed MiniMax-H3 for joint video and audio generation (INT8 and GGUF)
-
Updated
Nov 9, 2026 - Python
HyperFlow H3 Flash: Video Rebirth's 13.7B, 4- to 8-step compressed MiniMax-H3 for joint video and audio generation (INT8 and GGUF)
[ICLR 2026] dParallel: Learnable Parallel Decoding for dLLMs
✨ PyTorch implementation of "Cora: Correspondence-aware Image Editing Using Few-Step Diffusion", accepted at SIGGRAPH 2025.
[ECCV 2026] StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation
Turn a text prompt into a 1024×1024 image in 6 steps, locally with Qwen-Image-2.1, the P-Q-Image-2.1 LoRA and model-compose.
Progressive-resolution sampling for ComfyUI: run the early denoising steps at low resolution, lift the result to full resolution, and finish there — faster generation with no training.
Official PyTorch implementation of FLEX-MRI: Stochastic Finite-Transition Learning and Exploration for Accelerated MRI Reconstruction
Unofficial ComfyUI integration of NVlabs LongLive-Plug few-step/CFG adapters for Wan2.1-T2V-14B, with coverage checks and upstream-verified sampling recipes
To associate your repository with the few-step topic, visit your repo's landing page and select "manage topics."