Comfy-Org/ComfyUIPublic

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

AI summary: A powerful node-based GUI for designing and executing advanced Stable Diffusion generative workflows.

Stars
147.8K
+15 today
Forks
17.6K
Watchers
853
Open issues
4.5K
Open PRs
1.1K
Contributors
~363
Commits
6.4K
Branches
673
Views (30d)
5

PythonGPL-3.0Created Jan 17, 2023Last push todayLatest release v0.45.0+1K stars this week+5.8K this month

Quick answers

What is ComfyUI?
A powerful node-based GUI for designing and executing advanced Stable Diffusion generative workflows.
What does ComfyUI do?
ComfyUI provides a highly flexible visual programming environment for running complex image generation models. It operates by allowing users to connect distinct processing nodes to construct custom image generation pipelines without writing code. The architecture strictly separates the frontend interface from the backend execution engine to ensure stable and reproducible results. It supports an extensive range of advanced features, including custom model loading, granular latent space manipulation, and complex control net routing. The system is designed specifically to optimize memory usage and execution speed during intensive generation tasks.
Who is ComfyUI for?
AI artists and researchers requiring precise, granular control over Stable Diffusion image generation processes. Technical users looking to experiment with complex visual pipelines without being constrained by rigid user interfaces.
How do I get started with ComfyUI?
git clone https://github.com/comfyanonymous/ComfyUI.git
How popular is ComfyUI on GitHub?
Comfy-Org/ComfyUI has 147,848 stars and 17,605 forks on GitHub, and gained 1,011 stars in the last 7 days.
What license does ComfyUI use?
Comfy-Org/ComfyUI is released under the GPL-3.0 license.

Star history

since Jul 28, 2026
050K100KJul 2026Sep 2026Oct 2026Nov 2026
147.8K stars as of Nov 21, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

6 recorded
  • Nov 11, 2026New release v0.45.0 (previously v0.44.0).
  • Nov 4, 2026New release v0.44.0 (previously v0.43.0).
  • Oct 27, 2026New release v0.43.0 (previously v0.42.1).
  • Oct 20, 2026New release v0.42.1 (previously v0.40.0).
  • Oct 13, 2026New release v0.40.0 (previously v0.39.0).
  • Oct 6, 2026New release v0.39.0 (previously v0.37.0).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 2 commits2025-11-24: 6 commits2025-11-25: 15 commits2025-11-26: 12 commits2025-11-27: 6 commits2025-11-28: 7 commits2025-11-29: 6 commits2025-11-30: 2 commits2025-12-01: 6 commits2025-12-02: 9 commits2025-12-03: 8 commits2025-12-04: 3 commits2025-12-05: 10 commits2025-12-06: 8 commits2025-12-07: 2 commits2025-12-08: 9 commits2025-12-09: 9 commits2025-12-10: 3 commits2025-12-11: 8 commits2025-12-12: 4 commits2025-12-13: 1 commit2025-12-14: 2 commits2025-12-15: 9 commits2025-12-16: 11 commits2025-12-17: 8 commits2025-12-18: 6 commits2025-12-19: 9 commits2025-12-20: 6 commits2025-12-21: 1 commit2025-12-22: 2 commits2025-12-23: 3 commits2025-12-24: 3 commits2025-12-25: 2 commits2025-12-26: 1 commit2025-12-27: 6 commits2025-12-28: 1 commit2025-12-29: 2 commits2025-12-30: 6 commits2025-12-31: 3 commits2026-01-01: 2 commits2026-01-02: 4 commits2026-01-03: 1 commit2026-01-04: 4 commits2026-01-05: 5 commits2026-01-06: 11 commits2026-01-07: 16 commits2026-01-08: 9 commits2026-01-09: 8 commits2026-01-10: 4 commits2026-01-11: 2 commits2026-01-12: 6 commits2026-01-13: 13 commits2026-01-14: 9 commits2026-01-15: 5 commits2026-01-16: 4 commits2026-01-17: 3 commits2026-01-18: 6 commits2026-01-19: 7 commits2026-01-20: 7 commits2026-01-21: 6 commits2026-01-22: 11 commits2026-01-23: 4 commits2026-01-24: 5 commits2026-01-25: 3 commits2026-01-26: 6 commits2026-01-27: 6 commits2026-01-28: 2 commits2026-01-29: 5 commits2026-01-30: 5 commits2026-01-31: 7 commits2026-02-01: 5 commits2026-02-02: 5 commits2026-02-03: 16 commits2026-02-04: 9 commits2026-02-05: 5 commits2026-02-06: 6 commits2026-02-07: 3 commits2026-02-08: 3 commits2026-02-09: 3 commits2026-02-10: 10 commits2026-02-11: 9 commits2026-02-12: 5 commits2026-02-13: 5 commits2026-02-14: 3 commits2026-02-15: 6 commits2026-02-16: 5 commits2026-02-17: 9 commits2026-02-18: 5 commits2026-02-19: 5 commits2026-02-20: 8 commits2026-02-21: 8 commits2026-02-22: 2 commits2026-02-23: 3 commits2026-02-24: 8 commits2026-02-25: 8 commits2026-02-26: 10 commits2026-02-27: 9 commits2026-02-28: 10 commits2026-03-01: 5 commits2026-03-02: 2 commits2026-03-03: 9 commits2026-03-04: 8 commits2026-03-05: 15 commits2026-03-06: 7 commits2026-03-07: 4 commits2026-03-08: 2 commits2026-03-09: 4 commits2026-03-10: 5 commits2026-03-11: 5 commits2026-03-12: 11 commits2026-03-13: 5 commits2026-03-14: 6 commits2026-03-15: 6 commits2026-03-16: 7 commits2026-03-17: 8 commits2026-03-18: 8 commits2026-03-19: 8 commits2026-03-20: 6 commits2026-03-21: 4 commits2026-03-22: 2 commits2026-03-23: 1 commit2026-03-24: 8 commits2026-03-25: 5 commits2026-03-26: 7 commits2026-03-27: 6 commits2026-03-28: 3 commits2026-03-29: 4 commits2026-03-30: 2 commits2026-03-31: 1 commit2026-04-01: 2 commits2026-04-02: 1 commit2026-04-03: 3 commits2026-04-04: 1 commit2026-04-05: 2 commits2026-04-06: 3 commits2026-04-07: 2 commits2026-04-08: 1 commit2026-04-09: 2 commits2026-04-10: 2 commits2026-04-11: 4 commits2026-04-12: 2 commits2026-04-13: 5 commits2026-04-14: 5 commits2026-04-15: 4 commits2026-04-16: 2 commits2026-04-17: 6 commits2026-04-18: 3 commits2026-04-19: 3 commits2026-04-20: 1 commit2026-04-21: 9 commits2026-04-22: 5 commits2026-04-23: 15 commits2026-04-24: 5 commits2026-04-25: 2 commits2026-04-26: 2 commits2026-04-27: 5 commits2026-04-28: 7 commits2026-04-29: 6 commits2026-04-30: 5 commits2026-05-01: 9 commits2026-05-02: 4 commits2026-05-03: 12 commits2026-05-04: 8 commits2026-05-05: 18 commits2026-05-06: 6 commits2026-05-07: 7 commits2026-05-08: 13 commits2026-05-09: 4 commits2026-05-10: 4 commits2026-05-11: 8 commits2026-05-12: 9 commits2026-05-13: 6 commits2026-05-14: 9 commits2026-05-15: 5 commits2026-05-16: 3 commits2026-05-17: 1 commit2026-05-18: 11 commits2026-05-19: 8 commits2026-05-20: 9 commits2026-05-21: 14 commits2026-05-22: 11 commits2026-05-23: 3 commits2026-05-24: 2 commits2026-05-25: 7 commits2026-05-26: 9 commits2026-05-27: 9 commits2026-05-28: 8 commits2026-05-29: 9 commits2026-05-30: 3 commits2026-05-31: 6 commits2026-06-01: 10 commits2026-06-02: 5 commits2026-06-03: 6 commits2026-06-04: 10 commits2026-06-05: 9 commits2026-06-06: 3 commits2026-06-07: 1 commit2026-06-08: 7 commits2026-06-09: 10 commits2026-06-10: 11 commits2026-06-11: 9 commits2026-06-12: 4 commits2026-06-13: 6 commits2026-06-14: 2 commits2026-06-15: 6 commits2026-06-16: 8 commits2026-06-17: 9 commits2026-06-18: 6 commits2026-06-19: 6 commits2026-06-20: 5 commits2026-06-21: 0 commits2026-06-22: 3 commits2026-06-23: 8 commits2026-06-24: 7 commits2026-06-25: 7 commits2026-06-26: 1 commit2026-06-27: 3 commits2026-06-28: 1 commit2026-06-29: 2 commits2026-06-30: 8 commits2026-07-01: 5 commits2026-07-02: 4 commits2026-07-03: 5 commits2026-07-04: 3 commits2026-07-05: 3 commits2026-07-06: 3 commits2026-07-07: 6 commits2026-07-08: 2 commits2026-07-09: 9 commits2026-07-10: 13 commits2026-07-11: 3 commits2026-07-12: 1 commit2026-07-13: 8 commits2026-07-14: 4 commits2026-07-15: 6 commits2026-07-16: 4 commits2026-07-17: 4 commits2026-07-18: 5 commits2026-07-19: 1 commit2026-07-20: 2 commits2026-07-21: 7 commits2026-07-22: 3 commits2026-07-23: 5 commits2026-07-24: 2 commits2026-07-25: 6 commits2026-07-26: 2 commits2026-07-27: 4 commits2026-07-28: 6 commits2026-07-29: 9 commits2026-07-30: 4 commits2026-07-31: 11 commits2026-08-01: 12 commits2026-08-02: 5 commits2026-08-03: 8 commits2026-08-04: 3 commits2026-08-05: 6 commits2026-08-06: 8 commits2026-08-07: 11 commits2026-08-08: 7 commits2026-08-09: 2 commits2026-08-10: 4 commits2026-08-11: 12 commits2026-08-12: 9 commits2026-08-13: 5 commits2026-08-14: 9 commits2026-08-15: 5 commits2026-08-16: 3 commits2026-08-17: 6 commits2026-08-18: 5 commits2026-08-19: 2 commits2026-08-20: 7 commits2026-08-21: 3 commits2026-08-22: 3 commits2026-08-23: 4 commits2026-08-24: 4 commits2026-08-25: 5 commits2026-08-26: 6 commits2026-08-27: 5 commits2026-08-28: 4 commits2026-08-29: 3 commits2026-08-30: 2 commits2026-08-31: 2 commits2026-09-01: 5 commits2026-09-02: 8 commits2026-09-03: 9 commits2026-09-04: 8 commits2026-09-05: 9 commits2026-09-06: 12 commits2026-09-07: 5 commits2026-09-08: 9 commits2026-09-09: 11 commits2026-09-10: 6 commits2026-09-11: 4 commits2026-09-12: 8 commits2026-09-13: 4 commits2026-09-14: 7 commits2026-09-15: 10 commits2026-09-16: 6 commits2026-09-17: 7 commits2026-09-18: 3 commits2026-09-19: 2 commits2026-09-20: 11 commits2026-09-21: 5 commits2026-09-22: 6 commits2026-09-23: 6 commits2026-09-24: 10 commits2026-09-25: 7 commits2026-09-26: 3 commits2026-09-27: 4 commits2026-09-28: 9 commits2026-09-29: 11 commits2026-09-30: 7 commits2026-10-01: 7 commits2026-10-02: 7 commits2026-10-03: 7 commits2026-10-04: 4 commits2026-10-05: 9 commits2026-10-06: 8 commits2026-10-07: 8 commits2026-10-08: 6 commits2026-10-09: 8 commits2026-10-10: 4 commits2026-10-11: 2 commits2026-10-12: 4 commits2026-10-13: 8 commits2026-10-14: 4 commits2026-10-15: 9 commits2026-10-16: 5 commits2026-10-17: 6 commits2026-10-18: 12 commits2026-10-19: 4 commits2026-10-20: 6 commits2026-10-21: 12 commits2026-10-22: 7 commits2026-10-23: 16 commits2026-10-24: 2 commits2026-10-25: 1 commit2026-10-26: 5 commits2026-10-27: 4 commits2026-10-28: 10 commits2026-10-29: 4 commits2026-10-30: 3 commits2026-10-31: 5 commits2026-11-01: 2 commits2026-11-02: 4 commits2026-11-03: 11 commits2026-11-04: 10 commits2026-11-05: 5 commits2026-11-06: 9 commits2026-11-07: 5 commits2026-11-08: 3 commits2026-11-09: 2 commits2026-11-10: 11 commits2026-11-11: 4 commits2026-11-12: 7 commits2026-11-13: 8 commits2026-11-14: 3 commits2026-11-15: 7 commits2026-11-16: 4 commits2026-11-17: 9 commits2026-11-18: 4 commits2026-11-19: 0 commits2026-11-20: 0 commits2026-11-21: 0 commits
2,120 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Landmark project

    147,848 stars

  • Very active

    2,120 commits in 52 weeks

  • Community-driven

    ~363 contributors

  • Continuous integration

    Automated checks passing

  • Repeat trending

    23 trending appearances

  • Top 10% tracked

    Rank 43 of 1243

What ComfyUI does

ComfyUI provides a highly flexible visual programming environment for running complex image generation models. It operates by allowing users to connect distinct processing nodes to construct custom image generation pipelines without writing code. The architecture strictly separates the frontend interface from the backend execution engine to ensure stable and reproducible results. It supports an extensive range of advanced features, including custom model loading, granular latent space manipulation, and complex control net routing. The system is designed specifically to optimize memory usage and execution speed during intensive generation tasks.

AI artists and researchers requiring precise, granular control over Stable Diffusion image generation processes. Technical users looking to experiment with complex visual pipelines without being constrained by rigid user interfaces.

  • Node architecture: Connects individual processing steps visually to create highly customized image generation pipelines.
  • Workflow serialization: Saves entire complex node graphs as JSON data embedded directly within generated image files.
  • Model compatibility: Supports SD1.x, SD2.x, SDXL, and ControlNet architectures seamlessly within the same interface.
  • Asynchronous execution: Processes rendering tasks entirely in the background without blocking the main user interface.
  • Memory management: Optimizes VRAM usage dynamically to support extremely large image resolutions on consumer hardware.

Where teams use it

Advanced image generation

Design intricate multi-step rendering pipelines to achieve precise artistic control over AI outputs.

Workflow sharing

Distribute complex generation setups by sharing single output images containing embedded configuration data.

Model testing

Compare outputs from multiple different checkpoints simultaneously using branched node networks.

Automated batch processing

Queue large batches of prompt variations to run unattended through complex upscaling and refinement pipelines.

Getting started: git clone https://github.com/comfyanonymous/ComfyUI.git

README

master branch

ComfyUI

The most powerful and modular AI engine for content creation.

Website Dynamic JSON Badge Twitter Matrix

ComfyUI Screenshot

ComfyUI is the AI creation engine for visual professionals who demand control over every model, every parameter, and every output. Its powerful and modular node graph interface empowers creatives to generate images, videos, 3D models, audio, and more...

  • ComfyUI natively supports the latest open-source state of the art models.
  • It is by far the most optimized inference engine for diffusion models in the world with a focus on local consumer hardware.
  • Can run even the biggest open source models on as low as 4GB vram + 8GB ram relatively quickly (saturating your GPU compute) using our state of the art asynchronous weight streaming technology.
  • Partner nodes provide access to the best closed source models such as Nano Banana, Seedance, Hunyuan3D, etc.
  • It is available on Windows, Linux, and macOS, locally with our desktop application, our portable install or on our cloud.
  • The most sophisticated workflows can be exposed through a simple UI thanks to App Mode.
  • It integrates seamlessly into production pipelines with our API endpoints.

Get Started

Local

  • The easiest way to get started.
  • Available on Windows & macOS.

Supports all operating systems and GPU types (NVIDIA, AMD, Intel, Apple Silicon, Ascend).

Cloud

  • Our official paid cloud version for those who can't afford local hardware.

Examples

See what ComfyUI can do with the newer template workflows or old example workflows.

Features

  • A visual node graph for building and reusing image, video, audio, 3D, and text workflows without code.
  • Reusable subgraphs, workflow templates, App Mode, and a local API for integrating workflows into applications.
  • Efficient local execution with asynchronous queueing, partial graph re-execution, smart VRAM and RAM management, model offloading, and support for quantized models.
  • Broad native model support. This is a representative list; browse the workflow library for maintained, ready-to-run templates.
    • Image generation: Stable Diffusion 1.5, SDXL, SD3.5, Flux.1, Flux.2, Qwen Image, Z-Image, Hunyuan Image 2.1, HiDream, Lumina Image 2.0, Chroma, Anima, LongCat Image, Ideogram 4, Krea 2, MageFlow, Microsoft Lens, PixelDiT, Kandinsky 5, Ernie Image and Moss Image.
    • Image editing: Flux Kontext, Flux.2 Klein, Qwen Image Edit, HiDream E1.1 and O1, OmniGen2, Boogu, JoyImage Edit, MageFlow Edit, LongCat Image Edit, Fibo 2.0, Flux 3 image klein.
    • Video generation: Wan 2.1 and 2.2, LTX-Video 2 and 2.3, HunyuanVideo 1.5, Kandinsky 5 Video, CogVideoX, Cosmos Predict2, Bernini-R, SCAIL 2, and Mochi.
    • Audio and video generation: MiniMax H3 and LTX-AV.
    • Audio generation: ACE-Step 1.5, Stable Audio 3, MiniMax Music 3 and Yue 2.
    • 3D and vision: Hunyuan3D 2.1, TripoSplat, SeedVR2, SUPIR, Depth Anything 3, MoGe, SAM 3 and 3.1, RT-DETRv4, and BiRefNet.
    • Text generation: Gemma 3 and 4, Qwen3, Qwen3.5, and Qwen3-VL, including multimodal inputs.
  • Load complete checkpoints or separate diffusion models, VAEs, text encoders, LoRAs, ControlNets, adapters, and upscalers from supported model formats.
  • Built-in tools for inpainting, outpainting, reference conditioning, masks and compositing, model merging, upscaling, frame interpolation, segmentation, depth estimation, and media processing.
  • Save and load workflows as JSON, or recover complete workflows and seeds from supported generated media.
  • Runs fully offline: core does not download anything unless you request it. Use --offline to disable the optional paid Comfy API nodes and force all built-in functionality to stay offline, or --disable-partner-nodes to only disable the API nodes.
  • Extend ComfyUI with custom nodes
  • Configure additional model locations with extra_model_paths.yaml.
  • Support for saving and loading high bit depth images and videos: 16 bit PNG images, 32 bit EXR, 10 bit AVIF are supported and more.
  • Support for saving and loading HDR videos and images in various formats.

Release Process

ComfyUI follows a weekly release cycle targeting Monday but this regularly changes because of model releases or large changes to the codebase. There are three interconnected repositories:

  1. ComfyUI Core

    • Releases a new major stable version (e.g., v0.7.0) roughly every 2 weeks.
    • Starting from v0.4.0 patch versions will be used for fixes backported onto the current stable release.
    • Minor versions will be used for releases off the master branch.
    • Patch versions may still be used for releases on the master branch in cases where a backport would not make sense.
    • Commits outside of the stable release tags may be very unstable and break many custom nodes.
    • Serves as the foundation for the desktop release
  2. Comfy Desktop

    • Builds a new release using the latest stable core version
  3. ComfyUI Frontend

    • Every 2+ weeks frontend updates are merged into the core repository
    • Features are frozen for the upcoming core release
    • Development continues for the next release cycle

Shortcuts

Keybind Explanation
Ctrl + Enter Queue up current graph for generation
Ctrl + Shift + Enter Queue up current graph as first for generation
Ctrl + Alt + Enter Cancel current generation
Ctrl + Z/Ctrl + Y Undo/Redo
Ctrl + S Save workflow
Ctrl + O Load workflow
Ctrl + A Select all nodes
Alt + C Collapse/uncollapse selected nodes
Ctrl + M Mute/unmute selected nodes
Ctrl + B Bypass selected nodes (acts like the node was removed from the graph and the wires reconnected through)
Delete/Backspace Delete selected nodes
Ctrl + Backspace Delete the current graph
Space Move the canvas around when held and moving the cursor
Ctrl/Shift + Click Add clicked node to selection
Ctrl + C/Ctrl + V Copy and paste selected nodes (without maintaining connections to outputs of unselected nodes)
Ctrl + C/Ctrl + Shift + V Copy and paste selected nodes (maintaining connections from outputs of unselected nodes to inputs of pasted nodes)
Shift + Drag Move multiple selected nodes at the same time
Ctrl + D Load default graph
Alt + + Canvas Zoom in
Alt + - Canvas Zoom out
Ctrl + Shift + LMB + Vertical drag Canvas Zoom in/out
P Pin/Unpin selected nodes
Ctrl + G Group selected nodes
Q Toggle visibility of the queue
H Toggle visibility of history
R Refresh graph
F Show/Hide menu
. Fit view to selection (Whole graph when nothing is selected)
Double-Click LMB Open node quick search palette
Shift + Drag Move multiple wires at once
Ctrl + Alt + LMB Disconnect all wires from clicked slot

Ctrl can also be replaced with Cmd instead for macOS users

Installing

Windows and Mac

We highly recommend using the desktop app:

The desktop app is the easiest and best way to use ComfyUI for new users.

Windows Portable

There is a portable standalone build for Windows that should work for running on Nvidia GPUs or for running on your CPU only. It is not recommended for regular users. Regular users should use the desktop app above.

Direct link to download (nvidia)

Simply download, extract with 7-Zip or with the windows explorer on recent windows versions and run. For smaller models you normally only need to put the checkpoints (the huge ckpt/safetensors files) in: ComfyUI\models\checkpoints but many of the larger models have multiple files. Make sure to follow the instructions to know which subfolder to put them in ComfyUI\models\

If you have trouble extracting it, right click the file -> properties -> unblock

The portable above currently comes with python 3.13 and pytorch cuda 13.0. Update your Nvidia drivers if it doesn't start.

All Official Portable Downloads:

Portable for AMD GPUs

Portable for Intel GPUs

Portable for Nvidia GPUs (supports 20 series and above).

Portable for Nvidia GPUs with pytorch cuda 12.6 and python 3.12 (Supports Nvidia 10 series and older GPUs, DO NOT USE THIS ON NEWER 20 SERIES AND ABOVE GPUS).

How do I share models between another UI and ComfyUI?

See the Config file to set the search paths for models. In the standalone windows build you can find this file in the ComfyUI directory. Rename this file to extra_model_paths.yaml and edit it with your favorite text editor.

You can install and start ComfyUI using comfy-cli:

pip install comfy-cli
comfy install

Manual Install (Windows, Linux)

Python 3.14 works but some custom nodes may have issues. The free threaded variant works but some dependencies will enable the GIL so it's not fully supported.

Python 3.13 is very well supported. If you have trouble with some custom node dependencies on 3.13 you can try 3.12

torch 2.7 is minimally supported but using a newer version is extremely recommended. Using a cu130 or above version of pytorch is required on Nvidia 20 series and above. Some features and optimizations might only work on newer versions. We generally recommend using the latest major version of pytorch with the latest cuda version unless it is less than 2 weeks old. If your pytorch is more than 6 months old, please update it.

Instructions:

Git clone this repo.

Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints

Put your VAE in: models/vae

AMD GPUs (Linux)

AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version:

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm7.2

This is the command to install the nightly with ROCm 7.2 which might have some performance improvements:

pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.2

AMD GPUs (Windows, ROCm 10.0)

Use AMD's multi-architecture PyTorch packages. The device-* extras install your GPU's kernels and the matching ROCm runtime automatically; a separate HIP SDK installation is not needed.

Use Windows 11, a current AMD graphics driver, and 64-bit Python 3.13.

The install command below uses device-all to install kernels for all supported GPUs. To reduce download size and disk usage, optionally replace both occurrences of device-all with the target for your GPU:

GPU Device extra
RX 9070 / XT, Radeon AI PRO R9700 device-gfx1201
RX 9060 / XT device-gfx1200
RX 7900 XT / XTX device-gfx1100
RX 7700 XT / 7800 XT device-gfx1101
RX 7600 / XT device-gfx1102
Ryzen AI Max / Max+ (Strix Halo) device-gfx1151

Note: This table only lists examples. A GPU missing from it may still be supported: supported architectures include RDNA 2, RDNA 3, RDNA 3.5, and RDNA 4. Keep device-all to install kernels for all supported targets. For other models, see AMD's GPU target table and ROCm compatibility matrix.

ROCm 10.0.0 with PyTorch 2.13:

pip install --index-url https://stable.repo.amd.com/rocm/whl-next/ "torch[device-all]==2.13.0+rocm10.0.0" "torchvision[device-all]==0.28.0+rocm10.0.0" "torchaudio==2.11.0.2+rocm10.0.0"

Intel GPUs (Windows and Linux)

Intel Arc GPU users can install native PyTorch with torch.xpu support using pip. More information can be found here

  1. To install PyTorch xpu, use the following command:

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu

This is the command to install the Pytorch xpu nightly which might have some performance improvements:

pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/xpu

NVIDIA

Nvidia users should install stable pytorch using this command:

pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130

This is the command to install pytorch nightly instead which might have performance improvements.

pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu132

Troubleshooting

If you get the "Torch not compiled with CUDA enabled" error, uninstall torch with:

pip uninstall torch

And install it again with the command above.

Dependencies

Install the dependencies by opening your terminal inside the ComfyUI folder and:

pip install -r requirements.txt

After this you should have everything installed and can proceed to running ComfyUI.

Others:

Apple Mac silicon

You can install ComfyUI in Apple Mac silicon (M1, M2, M3 or M4) with any recent macOS version.

  1. Install pytorch nightly. For instructions, read the Accelerated PyTorch training on Mac Apple Developer guide (make sure to install the latest pytorch nightly).
  2. Follow the ComfyUI manual installation instructions for Windows and Linux.
  3. Install the ComfyUI dependencies. If you have another Stable Diffusion UI you might be able to reuse the dependencies.
  4. Launch ComfyUI by running python main.py

Note: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in ComfyUI manual installation.

Huawei Ascend NPUs

For models compatible with Huawei Ascend Extension for PyTorch (torch_npu). To get started, ensure your environment meets the prerequisites outlined on the installation page. Here's a step-by-step guide tailored to your platform and installation method:

  1. Begin by installing the recommended or newer kernel version for Linux as specified in the Installation page of torch-npu, if necessary.
  2. Proceed with the installation of Ascend Basekit, which includes the driver, firmware, and CANN, following the instructions provided for your specific platform.
  3. Next, install the necessary packages for torch-npu by adhering to the platform-specific instructions on the Installation page.
  4. Finally, adhere to the ComfyUI manual installation guide for Linux. Once all components are installed, you can run ComfyUI as described earlier.
Cambricon MLUs

For models compatible with Cambricon Extension for PyTorch (torch_mlu). Here's a step-by-step guide tailored to your platform and installation method:

  1. Install the Cambricon CNToolkit by adhering to the platform-specific instructions on the Installation
  2. Next, install the PyTorch(torch_mlu) following the instructions on the Installation
  3. Launch ComfyUI by running python main.py
Iluvatar Corex

For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step guide tailored to your platform and installation method:

  1. Install the Iluvatar Corex Toolkit by adhering to the platform-specific instructions on the Installation
  2. Launch ComfyUI by running python main.py

ComfyUI-Manager is an extension that allows you to easily install, update, and manage custom nodes for ComfyUI.

Setup

  1. Install the manager dependencies:

    pip install -r manager_requirements.txt
  2. Enable the manager with the --enable-manager flag when running ComfyUI:

    python main.py --enable-manager

Command Line Options

Flag Description
--enable-manager Enable ComfyUI-Manager
--enable-manager-legacy-ui Use the legacy manager UI instead of the new UI (implies --enable-manager)
--disable-manager-ui Disable the manager UI and endpoints while keeping background features like security checks and scheduled installation completion (requires --enable-manager)

Running

python main.py

For AMD cards not officially supported by ROCm

Try running it with this command if you have issues:

For 6700, 6600 and maybe other RDNA2 or older: HSA_OVERRIDE_GFX_VERSION=10.3.0 python main.py

For AMD 7600 and maybe other RDNA3 cards: HSA_OVERRIDE_GFX_VERSION=11.0.0 python main.py

AMD ROCm Tips

You can try setting this env variable PYTORCH_TUNABLEOP_ENABLED=1 which might speed things up at the cost of a very slow initial run.

Notes

Only parts of the graph that have an output with all the correct inputs will be executed.

Only parts of the graph that change from each execution to the next will be executed, if you submit the same graph twice only the first will be executed. If you change the last part of the graph only the part you changed and the part that depends on it will be executed.

Dragging a generated png on the webpage or loading one will give you the full workflow including seeds that were used to create it.

You can use () to change emphasis of a word or phrase like: (good code:1.2) or (bad code:0.8). The default emphasis for () is 1.1. To use () characters in your actual prompt escape them like \( or \).

You can use {day|night}, for wildcard/dynamic prompts. With this syntax "{wild|card|test}" will be randomly replaced by either "wild", "card" or "test" by the frontend every time you queue the prompt. To use {} characters in your actual prompt escape them like: \{ or \}.

Dynamic prompts also support C-style comments, like // comment or /* comment */.

To use a textual inversion concepts/embeddings in a text prompt put them in the models/embeddings directory and use them in the CLIPTextEncode node like this (you can omit the .pt extension):

embedding:embedding_filename.pt

How to show high-quality previews?

Use --preview-method auto to enable previews.

The default installation includes a fast latent preview method that's low-resolution. To enable higher-quality previews with TAESD, download the taesd_decoder.pth, taesdxl_decoder.pth, taesd3_decoder.pth and taef1_decoder.pth and place them in the models/vae_approx folder. Once they're installed, restart ComfyUI and launch it with --preview-method taesd to enable high-quality previews.

How to use TLS/SSL?

Generate a self-signed certificate (not appropriate for shared/production use) and key by running the command: openssl req -x509 -newkey rsa:4096 -keyout key.pem -out cert.pem -sha256 -days 3650 -nodes -subj "/C=XX/ST=StateName/L=CityName/O=CompanyName/OU=CompanySectionName/CN=CommonNameOrHostname"

Use --tls-keyfile key.pem --tls-certfile cert.pem to enable TLS/SSL, the app will now be accessible with https://... instead of http://....

Note: Windows users can use alexisrolland/docker-openssl or one of the 3rd party binary distributions to run the command example above.

If you use a container, note that the volume mount -v can be a relative path so ... -v ".\:/openssl-certs" ... would create the key & cert files in the current directory of your command prompt or powershell terminal.

Support and dev channel

Discord: Try the #help or #feedback channels.

Matrix space: #comfyui_space:matrix.org (it's like discord but open source).

See also: https://www.comfy.org/

psst — we're hiring! Help build ComfyUI: comfy.org/careers

Frontend Development

As of August 15, 2024, we have transitioned to a new frontend, which is now hosted in a separate repository: ComfyUI Frontend. The compiled JS files (from TS/Vue) are published to pypi and installed as a dependency in ComfyUI.

Reporting Issues and Requesting Features

For any bugs, issues, or feature requests related to the frontend, please use the ComfyUI Frontend repository. This will help us manage and address frontend-specific concerns more efficiently.

Using the Latest Frontend

The new frontend is now the default for ComfyUI. However, please note:

  1. The frontend in the main ComfyUI repository is updated fortnightly.
  2. Daily releases are available in the separate frontend repository.

To use the most up-to-date frontend version:

  1. For the latest daily release, launch ComfyUI with this command line argument:

    --front-end-version Comfy-Org/ComfyUI_frontend@latest
    
  2. For a specific version, replace latest with the desired version number:

    --front-end-version Comfy-Org/[email protected]
    

This approach allows you to easily switch between the stable fortnightly release and the cutting-edge daily updates, or even specific versions for testing purposes.

QA

Which GPU should I buy for this?

See this page for some recommendations

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

166 total
  1. v0.45.0v0.45.0Nov 10, 2026235.9K downloads

    ## What's Changed * Bump comfyui-frontend-package to 1.58.5 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/17442 * Add better error for when pixel_space VAE wrongly selected. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17518 * Make SeedVR2 VAE slice length adaptive to free memory by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17508 * [Partner Nodes] feat(Pika): add Pika H3 Flex nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17509 * [Partner Nodes] feat(Pika): add Pika Soundtrack, SFX and Music nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17328 * [Partner Nodes] feat(Tencent): add Tencent HY LLM node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17534 * Turn on local_web_sso and partner_node_token by default by @dante01yoon in https://github.com/Comfy-Org/ComfyUI/pull/17540 * Update workflow templates to v0.11.102 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17541 * Update comfy-kitchen version to 0.2.41 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17542 * Fix potential crash. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17543 *

  2. v0.44.0v0.44.0Nov 4, 2026193.8K downloads

    ## What's Changed * [Partner Nodes] feat(Patina): add Patina texture nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17384 * [Partner Nodes] feat(VEED): add VEED Dubbing node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17388 * Update workflow templates to v0.11.98 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17391 * Switch pylint py version to 3.12 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17398 * anonymous_file: bypass python for memfd_create by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/17386 * Bump comfyui-frontend-package to 1.58.1 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/17375 * Use the cached frontend for pinned versions without a v prefix. by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/17348 * Look up a pinned frontend release by its tag instead of listing every release. by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/17402 * Skip concat if only a single cond. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17413 * [Partner Nodes] feat(BFL): add 1080p, 2K and 4K targets to Flux Video Upscale V2 node by @bigcat88 i

  3. v0.43.0v0.43.0Oct 27, 2026218.5K downloads

    ## What's Changed * model_prefetch: syncrhonize all graph cleanups by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/17178 * Add rope scaling support to MOSS-image by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17172 * [Partner Nodes] Renew partner-node sign-in tokens in API nodes by @dante01yoon in https://github.com/Comfy-Org/ComfyUI/pull/16943 * [Partner Nodes] feat(HeyGen): add HeyGen Voice instant clone and text-to-speech by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17043 * [Partner Nodes] feat(ClarityAI): add Crystal Video Upscaler node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17192 * [Partner Nodes] feat(BFL): add 2K/4K resolutions to FLUX 3 Video nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17200 * Support MOSS-image color-depth control by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17206 * Add to Readme that MOSS image is supported. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17212 * [Partner Nodes] feat(BFL): add FLUX 3 Max nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17202 * fix: correct top-p sampling threshold by @curealb in https://github.com/Comf

  4. v0.42.1v0.42.1Oct 19, 2026225.9K downloads

    Fix some crashing issues a few users experienced when running the MOSS image template workflow.

  5. v0.42.0v0.42.0Oct 18, 20264.1K downloads

    ## What's Changed * [Partner Nodes] feat(Krea): add Krea 3 Image node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17067 * Update workflow templates to v0.11.85 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17068 * Use FLUX 3 Image in node display labels by @MaanavD in https://github.com/Comfy-Org/ComfyUI/pull/17075 * Better documentation about the comfy quant format. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17078 * Update workflow templates to v0.11.86 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17083 * feat: Add MOSS-image support by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17095 * [Partner Nodes] chore(Quiver): remove retired Arrow 1.x models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17102 * Update comfy-kitchen version to 0.2.38 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17107 * Use fused situ with MOSS-image by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17099 * Performance improvements for qwen 3.x (Part 2) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/17007 * Update workflow templates to v0.11.87 by @comfyui-wiki in https://git

Code frequency

additions and deletions
+499.2K-499.2KWeek of 2025-11-23: +5,696 linesWeek of 2025-11-23: -2,098 linesWeek of 2025-11-30: +4,139 linesWeek of 2025-11-30: -1,576 linesWeek of 2025-12-07: +1,336 linesWeek of 2025-12-07: -417 linesWeek of 2025-12-14: +3,661 linesWeek of 2025-12-14: -1,368 linesWeek of 2025-12-21: +549 linesWeek of 2025-12-21: -387 linesWeek of 2025-12-28: +973 linesWeek of 2025-12-28: -340 linesWeek of 2026-01-04: +7,385 linesWeek of 2026-01-04: -1,292 linesWeek of 2026-01-11: +3,096 linesWeek of 2026-01-11: -199 linesWeek of 2026-01-18: +5,815 linesWeek of 2026-01-18: -3,391 linesWeek of 2026-01-25: +10,245 linesWeek of 2026-01-25: -502 linesWeek of 2026-02-01: +2,993 linesWeek of 2026-02-01: -385 linesWeek of 2026-02-08: +2,333 linesWeek of 2026-02-08: -658 linesWeek of 2026-02-15: +6,145 linesWeek of 2026-02-15: -615 linesWeek of 2026-02-22: +2,841 linesWeek of 2026-02-22: -290 linesWeek of 2026-03-01: +12,991 linesWeek of 2026-03-01: -3,449 linesWeek of 2026-03-08: +3,098 linesWeek of 2026-03-08: -1,178 linesWeek of 2026-03-15: +2,494 linesWeek of 2026-03-15: -654 linesWeek of 2026-03-22: +499,150 linesWeek of 2026-03-22: -160 linesWeek of 2026-03-29: +2,076 linesWeek of 2026-03-29: -206 linesWeek of 2026-04-05: +49,395 linesWeek of 2026-04-05: -101 linesWeek of 2026-04-12: +1,110 linesWeek of 2026-04-12: -160 linesWeek of 2026-04-19: +9,218 linesWeek of 2026-04-19: -315 linesWeek of 2026-04-26: +33,682 linesWeek of 2026-04-26: -3,278 linesWeek of 2026-05-03: +12,415 linesWeek of 2026-05-03: -1,753 linesWeek of 2026-05-10: +28,283 linesWeek of 2026-05-10: -1,379 linesWeek of 2026-05-17: +9,442 linesWeek of 2026-05-17: -878 linesWeek of 2026-05-24: +33,137 linesWeek of 2026-05-24: -4,683 linesWeek of 2026-05-31: +10,848 linesWeek of 2026-05-31: -12,422 linesWeek of 2026-06-07: +14,070 linesWeek of 2026-06-07: -8,123 linesWeek of 2026-06-14: +26,702 linesWeek of 2026-06-14: -597 linesWeek of 2026-06-21: +1,956 linesWeek of 2026-06-21: -707 linesWeek of 2026-06-28: +1,763 linesWeek of 2026-06-28: -1,603 linesWeek of 2026-07-05: +9,126 linesWeek of 2026-07-05: -486 linesWeek of 2026-07-12: +4,374 linesWeek of 2026-07-12: -221 linesWeek of 2026-07-19: +2,402 linesWeek of 2026-07-19: -264 linesWeek of 2026-07-26: +2,262 linesWeek of 2026-07-26: -525 linesWeek of 2026-08-02: +9,455 linesWeek of 2026-08-02: -1,240 linesWeek of 2026-08-09: +7,284 linesWeek of 2026-08-09: -519 linesWeek of 2026-08-16: +15,976 linesWeek of 2026-08-16: -619 linesWeek of 2026-08-23: +14,187 linesWeek of 2026-08-23: -843 linesWeek of 2026-08-30: +7,629 linesWeek of 2026-08-30: -743 linesWeek of 2026-09-06: +69,583 linesWeek of 2026-09-06: -2,429 linesWeek of 2026-09-13: +29,871 linesWeek of 2026-09-13: -14,352 linesWeek of 2026-09-20: +6,604 linesWeek of 2026-09-20: -1,295 linesWeek of 2026-09-27: +8,906 linesWeek of 2026-09-27: -2,548 linesWeek of 2026-10-04: +9,762 linesWeek of 2026-10-04: -940 linesWeek of 2026-10-11: +4,556 linesWeek of 2026-10-11: -764 linesWeek of 2026-10-18: +9,468 linesWeek of 2026-10-18: -2,176 linesWeek of 2026-10-25: +4,309 linesWeek of 2026-10-25: -360 linesWeek of 2026-11-01: +4,126 linesWeek of 2026-11-01: -537 linesWeek of 2026-11-08: +4,861 linesWeek of 2026-11-08: -1,966 linesWeek of 2026-11-15: +6,930 linesWeek of 2026-11-15: -2,464 linesNov 23, 2025Nov 15, 2026
+1M lines added, -90.5K removed over the last year.

Commits per week

last 52 weeks
680Week of 2025-11-23: 54 commitsWeek of 2025-11-30: 46 commitsWeek of 2025-12-07: 36 commitsWeek of 2025-12-14: 51 commitsWeek of 2025-12-21: 18 commitsWeek of 2025-12-28: 19 commitsWeek of 2026-01-04: 57 commitsWeek of 2026-01-11: 42 commitsWeek of 2026-01-18: 46 commitsWeek of 2026-01-25: 34 commitsWeek of 2026-02-01: 49 commitsWeek of 2026-02-08: 38 commitsWeek of 2026-02-15: 46 commitsWeek of 2026-02-22: 50 commitsWeek of 2026-03-01: 50 commitsWeek of 2026-03-08: 38 commitsWeek of 2026-03-15: 47 commitsWeek of 2026-03-22: 32 commitsWeek of 2026-03-29: 14 commitsWeek of 2026-04-05: 16 commitsWeek of 2026-04-12: 27 commitsWeek of 2026-04-19: 40 commitsWeek of 2026-04-26: 38 commitsWeek of 2026-05-03: 68 commitsWeek of 2026-05-10: 44 commitsWeek of 2026-05-17: 57 commitsWeek of 2026-05-24: 47 commitsWeek of 2026-05-31: 49 commitsWeek of 2026-06-07: 48 commitsWeek of 2026-06-14: 42 commitsWeek of 2026-06-21: 29 commitsWeek of 2026-06-28: 28 commitsWeek of 2026-07-05: 39 commitsWeek of 2026-07-12: 32 commitsWeek of 2026-07-19: 26 commitsWeek of 2026-07-26: 48 commitsWeek of 2026-08-02: 48 commitsWeek of 2026-08-09: 46 commitsWeek of 2026-08-16: 29 commitsWeek of 2026-08-23: 31 commitsWeek of 2026-08-30: 43 commitsWeek of 2026-09-06: 55 commitsWeek of 2026-09-13: 39 commitsWeek of 2026-09-20: 48 commitsWeek of 2026-09-27: 52 commitsWeek of 2026-10-04: 47 commitsWeek of 2026-10-11: 38 commitsWeek of 2026-10-18: 59 commitsWeek of 2026-10-25: 32 commitsWeek of 2026-11-01: 46 commitsWeek of 2026-11-08: 38 commitsWeek of 2026-11-15: 24 commitsNov 23, 2025Nov 15, 2026
2.1K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 19 commitsSun 1:00 — 42 commitsSun 2:00 — 24 commitsSun 3:00 — 33 commitsSun 4:00 — 31 commitsSun 5:00 — 21 commitsSun 6:00 — 21 commitsSun 7:00 — 16 commitsSun 8:00 — 22 commitsSun 9:00 — 18 commitsSun 10:00 — 16 commitsSun 11:00 — 28 commitsSun 12:00 — 28 commitsSun 13:00 — 43 commitsSun 14:00 — 21 commitsSun 15:00 — 37 commitsSun 16:00 — 22 commitsSun 17:00 — 36 commitsSun 18:00 — 25 commitsSun 19:00 — 22 commitsSun 20:00 — 27 commitsSun 21:00 — 21 commitsSun 22:00 — 21 commitsSun 23:00 — 18 commitsMon 0:00 — 38 commitsMon 1:00 — 32 commitsMon 2:00 — 16 commitsMon 3:00 — 30 commitsMon 4:00 — 17 commitsMon 5:00 — 13 commitsMon 6:00 — 10 commitsMon 7:00 — 7 commitsMon 8:00 — 21 commitsMon 9:00 — 13 commitsMon 10:00 — 33 commitsMon 11:00 — 34 commitsMon 12:00 — 36 commitsMon 13:00 — 43 commitsMon 14:00 — 51 commitsMon 15:00 — 39 commitsMon 16:00 — 58 commitsMon 17:00 — 54 commitsMon 18:00 — 49 commitsMon 19:00 — 56 commitsMon 20:00 — 74 commitsMon 21:00 — 46 commitsMon 22:00 — 40 commitsMon 23:00 — 38 commitsTue 0:00 — 43 commitsTue 1:00 — 52 commitsTue 2:00 — 60 commitsTue 3:00 — 40 commitsTue 4:00 — 28 commitsTue 5:00 — 22 commitsTue 6:00 — 25 commitsTue 7:00 — 24 commitsTue 8:00 — 24 commitsTue 9:00 — 24 commitsTue 10:00 — 31 commitsTue 11:00 — 51 commitsTue 12:00 — 49 commitsTue 13:00 — 57 commitsTue 14:00 — 54 commitsTue 15:00 — 36 commitsTue 16:00 — 45 commitsTue 17:00 — 64 commitsTue 18:00 — 41 commitsTue 19:00 — 58 commitsTue 20:00 — 54 commitsTue 21:00 — 63 commitsTue 22:00 — 43 commitsTue 23:00 — 55 commitsWed 0:00 — 43 commitsWed 1:00 — 47 commitsWed 2:00 — 43 commitsWed 3:00 — 37 commitsWed 4:00 — 26 commitsWed 5:00 — 22 commitsWed 6:00 — 17 commitsWed 7:00 — 20 commitsWed 8:00 — 26 commitsWed 9:00 — 22 commitsWed 10:00 — 28 commitsWed 11:00 — 35 commitsWed 12:00 — 44 commitsWed 13:00 — 44 commitsWed 14:00 — 42 commitsWed 15:00 — 45 commitsWed 16:00 — 62 commitsWed 17:00 — 56 commitsWed 18:00 — 47 commitsWed 19:00 — 57 commitsWed 20:00 — 75 commitsWed 21:00 — 53 commitsWed 22:00 — 48 commitsWed 23:00 — 29 commitsThu 0:00 — 40 commitsThu 1:00 — 41 commitsThu 2:00 — 30 commitsThu 3:00 — 27 commitsThu 4:00 — 27 commitsThu 5:00 — 23 commitsThu 6:00 — 19 commitsThu 7:00 — 24 commitsThu 8:00 — 30 commitsThu 9:00 — 24 commitsThu 10:00 — 34 commitsThu 11:00 — 43 commitsThu 12:00 — 41 commitsThu 13:00 — 45 commitsThu 14:00 — 46 commitsThu 15:00 — 60 commitsThu 16:00 — 63 commitsThu 17:00 — 58 commitsThu 18:00 — 53 commitsThu 19:00 — 68 commitsThu 20:00 — 52 commitsThu 21:00 — 62 commitsThu 22:00 — 33 commitsThu 23:00 — 34 commitsFri 0:00 — 37 commitsFri 1:00 — 28 commitsFri 2:00 — 60 commitsFri 3:00 — 36 commitsFri 4:00 — 29 commitsFri 5:00 — 28 commitsFri 6:00 — 17 commitsFri 7:00 — 16 commitsFri 8:00 — 29 commitsFri 9:00 — 16 commitsFri 10:00 — 33 commitsFri 11:00 — 41 commitsFri 12:00 — 49 commitsFri 13:00 — 44 commitsFri 14:00 — 49 commitsFri 15:00 — 41 commitsFri 16:00 — 40 commitsFri 17:00 — 51 commitsFri 18:00 — 48 commitsFri 19:00 — 46 commitsFri 20:00 — 47 commitsFri 21:00 — 52 commitsFri 22:00 — 35 commitsFri 23:00 — 38 commitsSat 0:00 — 46 commitsSat 1:00 — 51 commitsSat 2:00 — 37 commitsSat 3:00 — 35 commitsSat 4:00 — 27 commitsSat 5:00 — 21 commitsSat 6:00 — 17 commitsSat 7:00 — 14 commitsSat 8:00 — 17 commitsSat 9:00 — 16 commitsSat 10:00 — 18 commitsSat 11:00 — 45 commitsSat 12:00 — 48 commitsSat 13:00 — 31 commitsSat 14:00 — 43 commitsSat 15:00 — 41 commitsSat 16:00 — 36 commitsSat 17:00 — 39 commitsSat 18:00 — 38 commitsSat 19:00 — 44 commitsSat 20:00 — 36 commitsSat 21:00 — 24 commitsSat 22:00 — 27 commitsSat 23:00 — 15 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Oct 28, 2026weekly#12+4,109
Oct 27, 2026weekly#12+4,109
Oct 26, 2026weekly#12+4,790
Oct 25, 2026weekly#10+4,648
Oct 24, 2026weekly#9+4,531
Oct 23, 2026weekly#12+4,375
Oct 22, 2026daily#3+1,206
Oct 22, 2026weekly#12+3,948
Oct 21, 2026daily#3+1,206
Oct 20, 2026daily#2+1,011
Oct 19, 2026daily#2+1,011
Aug 25, 2026daily#11+201
Aug 24, 2026daily#11+201
Aug 15, 2026weekly#14+3,122
Aug 14, 2026weekly#14+3,122