Fast kernel library for Diffusion inference with multiple compute backends.
☆200Sep 2, 2026Updated this week
Alternatives and similar repositories for comfy-kitchen
Users that are interested in comfy-kitchen are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [DEPRECATED]☆55Aug 24, 2026Updated last week
- ☆172Updated this week
- Advanced Image Stitching & Image Padding Node for ComfyUI☆32Aug 20, 2026Updated 2 weeks ago
- Official ConvRot implementation. A plug-and-play, convolution-like rotation module enabling efficient W4A4 quantization for diffusion mod…☆29Jul 3, 2026Updated 2 months ago
- ☆230Aug 25, 2026Updated last week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- AI Model Demand Offloading Allocator☆62Updated this week
- ComfyUI implemtation for NAG☆318Nov 3, 2025Updated 10 months ago
- Custom node to load models in INT8 for 1.5~2X Speed gains on 30 series cards.☆300Jun 26, 2026Updated 2 months ago
- ComfyUI-VRAM-Manager is an independent memory management custom node for ComfyUI. Provides Distorch memory management functionality for e…☆51Aug 26, 2026Updated last week
- flux distillation and stuff☆123Jun 22, 2025Updated last year
- ☆18Mar 14, 2026Updated 5 months ago
- Custom extension for benchmarking ComfyUI performance☆15Feb 17, 2026Updated 6 months ago
- ☆593Mar 18, 2026Updated 5 months ago
- Pushing the Frontier of Long Video Generation Standalone, inference-only release for minute-level multi-shot audio-video generation with…☆57Updated this week
- 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.
- ComfyUI Nodes for AsymFlow and pi-Flow☆186Updated this week
- Fork of SageAttention for Windows wheels and easy installation☆1,028Updated this week
- Cache-DiT Node for Comfyui☆306Aug 4, 2026Updated last month
- ☆1,297Updated this week
- DiT model quantizer for ComfyUI. Converts full-precision models to NVFP4/FP8 using comfy-kitchen☆23Jul 14, 2026Updated last month
- ComfyUI nodes for SCAIL-Pose preprocessing☆322Apr 15, 2026Updated 4 months ago
- CRT-Nodes is a collection of custom nodes for ComfyUI.☆134Updated this week
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆158Jul 9, 2026Updated last month
- Pre-compiled Python whl for Flash-attention, SageAttention, NATTEN, xFormer etc☆852Aug 18, 2026Updated 2 weeks ago
- 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.
- A custom ComfyUI node for MiniCPM vision-language models, supporting v4, v4.5, and v4 GGUF formats, enabling high-quality image captionin…☆154Aug 28, 2025Updated last year
- ☆414Dec 11, 2025Updated 8 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
- FSampler is a training‑free, sampler‑agnostic acceleration layer for diffusion sampling.☆133Feb 28, 2026Updated 6 months ago
- ☆478May 20, 2026Updated 3 months ago
- 对原始的qwen3_VQA节点的增强。其他功能保持不变，只增加了自动扫描prompt_generator文件夹功能。不新建节点组，只对原节点组进行增加与修改。☆22Mar 2, 2026Updated 6 months ago
- [CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration☆133Apr 30, 2026Updated 4 months ago
- This is a pre-built wheel of Triton 3.3.0 for Windows with Nvidia only + Proton☆44May 18, 2025Updated last year
- A ComfyUI custom node implementation of TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows.☆44Mar 6, 2026Updated 5 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- PainterVRAM lets you reserve a slice of GPU memory before ComfyUI starts processing, preventing out-of-memory crashes. Switch between man…☆45Jan 2, 2026Updated 8 months ago
- A repo to quantize diffusion models directly in ComfyUI☆119Jun 14, 2025Updated last year
- SD.Next Quantization Engine☆131Updated this week
- ☆96Apr 26, 2025Updated last year
- ☆103Aug 9, 2026Updated 3 weeks ago
- ☆119May 22, 2024Updated 2 years ago
- Fast INT4 model inference custom node for ComfyUI leveraging Tensor Cores.☆38Jul 10, 2026Updated last month