KsanaDiT: High-Performance DiT (Diffusion Transformer) Inference Framework for Video & Image Generation
☆62May 13, 2026Updated 2 months ago
Alternatives and similar repositories for KsanaDiT
Users that are interested in KsanaDiT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reading paper list for iCloud group☆14May 3, 2026Updated 2 months ago
- ☆544Jul 14, 2026Updated last week
- A Triton JIT runtime and ffi provider in C++☆37Updated this week
- Autonomous GPU kernel optimization system driven by AI agents.☆31Mar 29, 2026Updated 3 months ago
- Distributed parallel 3D-Causal-VAE for efficient training and inference☆50Aug 20, 2025Updated 11 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- High performance inference engine for diffusion models☆107Sep 5, 2025Updated 10 months ago
- PhotoVerse is a text-to-image generation system that produces personalized images from text prompts using a single facial photograph.☆34May 23, 2024Updated 2 years ago
- SyncNoise: Geometrically Consistent Noise Prediction for Text-based 3D Scene Editing☆19Dec 28, 2024Updated last year
- A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.☆24Jul 18, 2025Updated last year
- Official pytorch implementation of "Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use"☆20Sep 16, 2025Updated 10 months ago
- ☆32Apr 29, 2026Updated 2 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆427Jul 5, 2025Updated last year
- A parallelism VAE avoids OOM for high resolution image generation☆95May 8, 2026Updated 2 months ago
- official code repository of 《Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation》☆18Jul 10, 2026Updated last week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆32Jul 2, 2025Updated last year
- RefSTAR: Blind Facial Image Restoration with Reference Selection, Transfer, and Reconstruction (AAAI 2026)☆24Apr 13, 2026Updated 3 months ago
- ECCV2024, LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models☆18Aug 9, 2024Updated last year
- ☆22Apr 4, 2022Updated 4 years ago
- A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration☆17Jul 22, 2022Updated 4 years ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆263Dec 27, 2024Updated last year
- fake CUTLASS to get peformance☆26Apr 28, 2026Updated 2 months ago
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆33Apr 21, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- This is the official PyTorch implementation of TBSR. Our team received 2nd place (real data track) and 3rd place (synthetic track) in NTI…☆14Jun 11, 2022Updated 4 years ago
- flex-block-attn: an efficient block sparse attention computation library☆130Dec 26, 2025Updated 6 months ago
- [NeurlPS' 25] InstructRestore: Region-Customized Image Restoration with Human Instructions☆53Oct 23, 2025Updated 8 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆693Jul 4, 2026Updated 2 weeks ago
- ☆19Jul 7, 2023Updated 3 years ago
- MSLK (Meta Superintelligence Labs Kernels) is a collection of PyTorch GPU operator libraries that are designed and optimized for GenAI tr…☆121Updated this week
- The official codes of our CVPR2022 paper: A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift☆45Dec 8, 2022Updated 3 years ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆61Oct 27, 2025Updated 8 months ago
- [WIP] Better (FP8) attention for Hopper☆33Feb 24, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- FA4-based Relative Attention Kernel developed by TML and Colfax☆17Updated this week
- ☆148Aug 18, 2025Updated 11 months ago
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆30Jan 22, 2026Updated 5 months ago
- Code for Draft Attention☆103May 22, 2025Updated last year
- Kai's homepage:☆10Jul 9, 2026Updated last week
- [NeurIPS 2025] DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution☆83Dec 20, 2025Updated 7 months ago
- [CVPR 2022] Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis☆35Oct 31, 2022Updated 3 years ago