Official ConvRot implementation. A plug-and-play, convolution-like rotation module enabling efficient W4A4 quantization for diffusion models, achieving 4× memory savings and 2× faster inference with preserved image quality.
☆35Jul 3, 2026Updated 4 months ago
Alternatives and similar repositories for ConvRot
Users that are interested in ConvRot are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SD.Next Quantization Engine☆139Updated this week
- Fast INT4 model inference custom node for ComfyUI leveraging Tensor Cores.☆40Jul 10, 2026Updated 4 months ago
- [CVPR 2026 Oral, Best Paper Finalist] SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models☆109Nov 7, 2026Updated last week
- [ICML 2026] Official implementation for "DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing".☆29May 5, 2026Updated 6 months ago
- A repository of Python & PyTorch scripts which (currently) converts .safetensors models into scaled FP8 variants, utilizing gradient desc…☆26Aug 8, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- LLM-based character segmentation agent for ComfyUI based on SAM 3 and the SAM 3 Agent notebook☆29Dec 22, 2025Updated 10 months ago
- SDNQ support for ComfyUI☆20Jan 6, 2026Updated 10 months ago
- A family of image super-resolution models with purrfect pixels.☆15Apr 29, 2026Updated 6 months ago
- One click, and a crew of AI agents turns your novel into a complete film.☆21Jul 22, 2026Updated 3 months ago
- ☆22Nov 3, 2025Updated last year
- Utility scripts to quantize models in optimal ComfyUI formata.☆37Aug 21, 2026Updated 2 months ago
- Extension for Forge-based UIs (Forge, reForge, etc) and ComfyUI to replace CFG with Negative Rejection Steering☆17Sep 3, 2026Updated 2 months ago
- Custom node to load models in INT8 for 1.5~2X Speed gains on 30 series cards.☆314Jun 26, 2026Updated 4 months ago
- Official implementation of the paper "Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers" (CVPR 2026)☆35Jun 30, 2026Updated 4 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Wan: Open and Advanced Large-Scale Video Generative Models☆31Jul 28, 2025Updated last year
- [ICLR 2026] Block-wise Adaptive Caching for Accelerating Diffusion Policy☆19Jan 27, 2026Updated 9 months ago
- ☆15Oct 29, 2026Updated 2 weeks ago
- flux distillation and stuff☆121Jun 22, 2025Updated last year
- ☆196Updated this week
- [DEPRECATED]☆55Aug 24, 2026Updated 2 months ago
- Official Code of "UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution"☆25Oct 12, 2025Updated last year
- ☆29Sep 29, 2026Updated last month
- ☆15Oct 27, 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.
- ☆12Aug 17, 2026Updated 3 months ago
- [CVPR 2026 Highlight] Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers☆66Apr 24, 2026Updated 6 months ago
- [NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation☆123Jun 22, 2026Updated 4 months ago
- [CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration☆141Sep 21, 2026Updated last month
- ComfyUI SAM3 node based on transformers / 基于 transformers 框架的 SAM3分割节点☆21Jan 29, 2026Updated 9 months ago
- DiT model quantizer for ComfyUI. Converts full-precision models to NVFP4/FP8 using comfy-kitchen☆25Jul 14, 2026Updated 4 months ago
- LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: sy…☆29Sep 9, 2026Updated 2 months ago
- ☆16Jun 6, 2026Updated 5 months ago
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideo☆23Jun 30, 2026Updated 4 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Testing Percepta's claim that transformers can execute programs via 2D convex hull attention☆11Sep 7, 2026Updated 2 months ago
- Residual vector quantization for KV cache compression in large language model☆12Oct 22, 2024Updated 2 years ago
- [CVPR 2026] CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance☆47Mar 4, 2026Updated 8 months ago
- Local inference for small VLMs: host work per step stays flat, so the GPU is the only bottleneck☆28Nov 5, 2026Updated last week
- Ultimate Model Converter for ComfyUI using comfyui-kitchen - Convert between Transformers, FP32, FP16, FP8. INT8, NVFP4, INT8 Comvrot☆100Updated this week
- A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing☆36Sep 10, 2026Updated 2 months ago
- ☆13Mar 27, 2026Updated 7 months ago
Are these results useful?