wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-01-10 14:20:49 +08:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
patientx 2025-11-13 13:23:13 +03:00 committed by GitHub
parent 9747b75093
commit bdbf42ee05
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 380 additions and 267 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

647
README.md
View File

@ -1,311 +1,424 @@
<div align="center">
# ComfyUI-ZLUDA
# ComfyUI
**The most powerful and modular visual AI engine and application.**
Windows-only version of ComfyUI which uses ZLUDA to get better performance with AMD GPUs.
[![Website][website-shield]][website-url]
[![Dynamic JSON Badge][discord-shield]][discord-url]
[![Twitter][twitter-shield]][twitter-url]
[![Matrix][matrix-shield]][matrix-url]
<br>
[![][github-release-shield]][github-release-link]
[![][github-release-date-shield]][github-release-link]
[![][github-downloads-shield]][github-downloads-link]
[![][github-downloads-latest-shield]][github-downloads-link]
[matrix-shield]: https://img.shields.io/badge/Matrix-000000?style=flat&logo=matrix&logoColor=white
[matrix-url]: https://app.element.io/#/room/%23comfyui_space%3Amatrix.org
[website-shield]: https://img.shields.io/badge/ComfyOrg-4285F4?style=flat
[website-url]: https://www.comfy.org/
<!-- Workaround to display total user from https://github.com/badges/shields/issues/4500#issuecomment-2060079995 -->
[discord-shield]: https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Finvites%2Fcomfyorg%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&logo=discord&logoColor=white&label=Discord&color=green&suffix=%20total
[discord-url]: https://www.comfy.org/discord
[twitter-shield]: https://img.shields.io/twitter/follow/ComfyUI
[twitter-url]: https://x.com/ComfyUI
[github-release-shield]: https://img.shields.io/github/v/release/comfyanonymous/ComfyUI?style=flat&sort=semver
[github-release-link]: https://github.com/comfyanonymous/ComfyUI/releases
[github-release-date-shield]: https://img.shields.io/github/release-date/comfyanonymous/ComfyUI?style=flat
[github-downloads-shield]: https://img.shields.io/github/downloads/comfyanonymous/ComfyUI/total?style=flat
[github-downloads-latest-shield]: https://img.shields.io/github/downloads/comfyanonymous/ComfyUI/latest/total?style=flat&label=downloads%40latest
[github-downloads-link]: https://github.com/comfyanonymous/ComfyUI/releases
![ComfyUI Screenshot](https://github.com/user-attachments/assets/7ccaf2c1-9b72-41ae-9a89-5688c94b7abe)
</div>
*** Comfyui added partial AMD support with the official torch's , at the moment the supported GPU's on windows start from 7000 series and up. For more information about that go to the official comfyui github page. (https://github.com/comfyanonymous/ComfyUI). This fork is still the best solution for older gpu models and even with the official support, most of the cards performance numbers are near what is achieved with zluda AT THE MOMENT. (it would hopefully change as AMD make the official pytorch builds better). ***
ComfyUI lets you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart based interface. Available on Windows, Linux, and macOS.
<details>
<summary><strong>FOR THOSE THAT ARE GETTING TROJAN DETECTIONS IN NCCL.DLL IN ZLUDA FOLDER</strong></summary>
## Get Started
In the developer's words: "nccl.dll is a dummy file, it does nothing. When one of its functions is called, it will just return 'not supported' status. nccl.dll and cufftw.dll are dummy files introduced only for compatibility (to run applications that reject to start without them, but rarely or never use them).
#### [Desktop Application](https://www.comfy.org/download)
- The easiest way to get started.
- Available on Windows & macOS.
zluda.exe hijacks Windows API and injects some DLLs. Its behavior can be considered malicious by some antiviruses, but it does not hurt the user.
#### [Windows Portable Package](#installing)
- Get the latest commits and completely portable.
- Available on Windows.
The antiviruses, including Windows Defender on my computer, didn't detect them as malicious when I made the nightly build. But somehow the nightly build is now detected as a virus on my end too."
#### [Manual Install](#manual-install-windows-linux)
Supports all operating systems and GPU types (NVIDIA, AMD, Intel, Apple Silicon, Ascend).
**SOLUTION: IGNORE THE WARNING AND EXCLUDE THE ZLUDA (or better the whole comfyui-zluda) FOLDER FROM DEFENDER.**
</details>
## [Examples](https://comfyanonymous.github.io/ComfyUI_examples/)
See what ComfyUI can do with the [example workflows](https://comfyanonymous.github.io/ComfyUI_examples/).
<details>
<summary><strong>What's New?</strong></summary>
## Features
- Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything.
- Image Models
- SD1.x, SD2.x ([unCLIP](https://comfyanonymous.github.io/ComfyUI_examples/unclip/))
- [SDXL](https://comfyanonymous.github.io/ComfyUI_examples/sdxl/), [SDXL Turbo](https://comfyanonymous.github.io/ComfyUI_examples/sdturbo/)
- [Stable Cascade](https://comfyanonymous.github.io/ComfyUI_examples/stable_cascade/)
- [SD3 and SD3.5](https://comfyanonymous.github.io/ComfyUI_examples/sd3/)
- Pixart Alpha and Sigma
- [AuraFlow](https://comfyanonymous.github.io/ComfyUI_examples/aura_flow/)
- [HunyuanDiT](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_dit/)
- [Flux](https://comfyanonymous.github.io/ComfyUI_examples/flux/)
- [Lumina Image 2.0](https://comfyanonymous.github.io/ComfyUI_examples/lumina2/)
- [HiDream](https://comfyanonymous.github.io/ComfyUI_examples/hidream/)
- [Qwen Image](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/)
- [Hunyuan Image 2.1](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_image/)
- Image Editing Models
- [Omnigen 2](https://comfyanonymous.github.io/ComfyUI_examples/omnigen/)
- [Flux Kontext](https://comfyanonymous.github.io/ComfyUI_examples/flux/#flux-kontext-image-editing-model)
- [HiDream E1.1](https://comfyanonymous.github.io/ComfyUI_examples/hidream/#hidream-e11)
- [Qwen Image Edit](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/#edit-model)
- Video Models
- [Stable Video Diffusion](https://comfyanonymous.github.io/ComfyUI_examples/video/)
- [Mochi](https://comfyanonymous.github.io/ComfyUI_examples/mochi/)
- [LTX-Video](https://comfyanonymous.github.io/ComfyUI_examples/ltxv/)
- [Hunyuan Video](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_video/)
- [Wan 2.1](https://comfyanonymous.github.io/ComfyUI_examples/wan/)
- [Wan 2.2](https://comfyanonymous.github.io/ComfyUI_examples/wan22/)
- Audio Models
- [Stable Audio](https://comfyanonymous.github.io/ComfyUI_examples/audio/)
- [ACE Step](https://comfyanonymous.github.io/ComfyUI_examples/audio/)
- 3D Models
- [Hunyuan3D 2.0](https://docs.comfy.org/tutorials/3d/hunyuan3D-2)
- Asynchronous Queue system
- Many optimizations: Only re-executes the parts of the workflow that changes between executions.
- Smart memory management: can automatically run large models on GPUs with as low as 1GB vram with smart offloading.
- Works even if you don't have a GPU with: ```--cpu``` (slow)
- Can load ckpt and safetensors: All in one checkpoints or standalone diffusion models, VAEs and CLIP models.
- Safe loading of ckpt, pt, pth, etc.. files.
- Embeddings/Textual inversion
- [Loras (regular, locon and loha)](https://comfyanonymous.github.io/ComfyUI_examples/lora/)
- [Hypernetworks](https://comfyanonymous.github.io/ComfyUI_examples/hypernetworks/)
- Loading full workflows (with seeds) from generated PNG, WebP and FLAC files.
- Saving/Loading workflows as Json files.
- Nodes interface can be used to create complex workflows like one for [Hires fix](https://comfyanonymous.github.io/ComfyUI_examples/2_pass_txt2img/) or much more advanced ones.
- [Area Composition](https://comfyanonymous.github.io/ComfyUI_examples/area_composition/)
- [Inpainting](https://comfyanonymous.github.io/ComfyUI_examples/inpaint/) with both regular and inpainting models.
- [ControlNet and T2I-Adapter](https://comfyanonymous.github.io/ComfyUI_examples/controlnet/)
- [Upscale Models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)](https://comfyanonymous.github.io/ComfyUI_examples/upscale_models/)
- [GLIGEN](https://comfyanonymous.github.io/ComfyUI_examples/gligen/)
- [Model Merging](https://comfyanonymous.github.io/ComfyUI_examples/model_merging/)
- [LCM models and Loras](https://comfyanonymous.github.io/ComfyUI_examples/lcm/)
- Latent previews with [TAESD](#how-to-show-high-quality-previews)
- Works fully offline: core will never download anything unless you want to.
- Optional API nodes to use paid models from external providers through the online [Comfy API](https://docs.comfy.org/tutorials/api-nodes/overview).
- [Config file](extra_model_paths.yaml.example) to set the search paths for models.
### Recent Updates
Workflow examples can be found on the [Examples page](https://comfyanonymous.github.io/ComfyUI_examples/)
- **Changed node storage folder and added CFZ-Condition-Caching node. This allows you to save-load conditionings -prompts basically- it helps on two fronts, if you are using same prompts over and over it skips the clip part AND more importantly it skips loading clip model all together, giving you more memory to load other stuff, main model being the most important. (It is based on this nodepack , https://github.com/alastor-666-1933/caching_to_not_waste)
## Release Process
<img width="1292" height="979" alt="Screenshot 2025-09-02 182907" src="https://github.com/user-attachments/assets/e7ab712b-4adc-426a-932a-acd0e49a30e0" />
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:
* I also uploaded an example workflow on how to use the nodes in your workflows. It is not fully working , and it is there to an idea how to incorporate to your workflows.
1. **[ComfyUI Core](https://github.com/comfyanonymous/ComfyUI)**
- Releases a new stable version (e.g., v0.7.0) roughly every week.
- Commits outside of the stable release tags may be very unstable and break many custom nodes.
- Serves as the foundation for the desktop release
- **Added "cfz-vae-loader" node** to CFZ folder - enables changing VAE precision on the fly without using `--fp16-vae` etc. on the starting command line. This is important because while "WAN" works faster with fp16, Flux produces black output if fp16 VAE is used. Start ComfyUI normally and add this node to your WAN workflow to change it only with that model type.
2. **[ComfyUI Desktop](https://github.com/Comfy-Org/desktop)**
- Builds a new release using the latest stable core version
- **Use update.bat** if comfyui.bat or comfyui-n.bat can't update (as when they are the files that need to be updated, so delete them, run update.bat). When you run your comfyui(-n).bat afterwards, it now copies correct ZLUDA and uses that.
3. **[ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend)**
- Weekly frontend updates are merged into the core repository
- Features are frozen for the upcoming core release
- Development continues for the next release cycle
- **Updated included ZLUDA version** for the new install method to 3.9.5 nightly (latest version available). You MUST use latest AMD GPU drivers with this setup otherwise there would be problems later (drivers >= 25.5.1).
## Shortcuts
### Cache Cleaning Instructions
| 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 |
**WIPING CACHES FOR A CLEAN REINSTALL** (recommended for a painless ZLUDA experience):
`Ctrl` can also be replaced with `Cmd` instead for macOS users
Delete everything in these three directories:
1. `C:\Users\yourusername\AppData\Local\ZLUDA\ComputeCache`
2. `C:\Users\yourusername\.miopen`
3. `C:\Users\yourusername\.triton`
You can now use the `cache-clean.bat` in the comfyui-zluda folder to clean all caches quickly.
# Installing
ZLUDA, MIOpen, and Triton will rebuild everything from scratch, making future operations less problematic.
## Windows Portable
### New Nodes
There is a portable standalone build for Windows that should work for running on Nvidia GPUs or for running on your CPU only on the [releases page](https://github.com/comfyanonymous/ComfyUI/releases).
- **Added "CFZ Cudnn Toggle" node** - for some models not working with cuDNN (which is enabled by default on new install method). To use it:
- Connect it before KSampler (latent_image input or any latent input)
- Disable cuDNN
- After VAE decoding (where most problems occur), re-enable cuDNN
- Add it after VAE decoding, select audio_output and connect to save audio node
- Enable cuDNN now
### [Direct link to download](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia.7z)
- **"CFZ Checkpoint Loader" was completely redone** - the previous version was broken and might corrupt models if you loaded with it and quit halfway. The new version works outside checkpoint loading, doesn't touch the original file, and when it quantizes the model, it makes a copy first.
- Please delete "cfz_checkpoint_loader.py" and use the newly added "cfz_patcher.py"
- It has three separate nodes and is much safer and better
Simply download, extract with [7-Zip](https://7-zip.org) and run. Make sure you put your Stable Diffusion checkpoints/models (the huge ckpt/safetensors files) in: ComfyUI\models\checkpoints
**Note**: Both nodes are inside the "cfz" folder. To use them, copy them into custom_nodes - they will appear next time you open ComfyUI. To find them, search for "cfz".
If you have trouble extracting it, right click the file -> properties -> unblock
### Model Fixes
Update your Nvidia drivers if it doesn't start.
- **Florence2 is now fixed** (probably some other nodes too) - you need to disable "do_sample", meaning change it from True to False. Now it works without needing to edit its node.
#### Alternative Downloads:
### Custom ZLUDA Versions
[Experimental portable for AMD GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_amd.7z)
- **Added support for any ZLUDA version** - to use with HIP versions you want (such as 6.1 - 6.2). After installing:
1. Close the app
2. Run `patchzluda2.bat`
3. It will ask for URL of the ZLUDA build you want to use
4. Choose from [lshyqqtiger's ZLUDA Fork](https://github.com/lshqqytiger/ZLUDA/releases)
5. Paste the link via right-click (correct link example: `https://github.com/lshqqytiger/ZLUDA/releases/download/rel.d60bddbc870827566b3d2d417e00e1d2d8acc026/ZLUDA-windows-rocm6-amd64.zip`)
6. Press enter and it will patch that ZLUDA into ComfyUI for you
[Portable with pytorch cuda 12.8 and python 3.12](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu128.7z) (Supports Nvidia 10 series and older GPUs).
### Documentation
#### How do I share models between another UI and ComfyUI?
- **Added a "Small Flux Guide"** - aims to use low VRAM and provides the basic necessary files needed to get Flux generation running. [View Guide](fluxguide.md)
See the [Config file](extra_model_paths.yaml.example) 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.
</details>
## Dependencies
* Install GIT from `https://git-scm.com/download/win` During installation don't forget to check the box for "Use Git from the Windows Command line and also from 3rd-party-software" to add Git to your system's PATH.
* Install python 3.11.9 or higher from python website `https://www.python.org/downloads/windows/` (not from Microsoft Store on Windows) Make sure you check the box for "Add Python to PATH when you are at the "Customize Python" screen.
* Install visual c++ runtime library from `https://aka.ms/vs/17/release/vc_redist.x64.exe`
## Setup (Windows-Only)
<details>
<summary>For Old Ryzen APU's, RX400-500 Series GPU's</summary>
* Install HIP SDK 5.7.1 from "https://www.amd.com/en/developer/resources/rocm-hub/hip-sdk.html", "Windows 10 & 11 5.7.1 HIP SDK"
* You *might* need older drivers for sdk 5.7.1 and old zluda to work so if you are getting errors with latest drivers please install an older version (below 25.5.1)
* Install "https://aka.ms/vs/17/release/vs_BuildTools.exe"
* Make sure the system variables HIP_PATH and HIP_PATH_57 exist, both should have this value: `C:\Program Files\AMD\ROCm\5.7\`
* Also there is the system path defining variable called: "Path". Double-click it and click "New" add this: `C:\Program Files\AMD\ROCm\5.7\bin`
* Get library files for your GPU from Brknsoul Repository (for HIP 5.7.1) `https://github.com/brknsoul/ROCmLibs`
* (try these for many of the old gpu's as an alternative source of libraries `https://www.mediafire.com/file/boobrm5vjg7ev50/rocBLAS-HIP5.7.1-win%2528old_gpu%2529.rar/file`)
* Go to folder `C:\Program Files\AMD\ROCm\5.7\bin\rocblas`, there would be a "library" folder, backup the files inside to somewhere else.
* Open your downloaded optimized library archive and put them inside the library folder (overwriting if necessary): `C:\Program Files\AMD\ROCm\5.7\bin\rocblas\library`
* There could be a rocblas.dll file in the archive as well, if it is present then copy it inside `C:\Program Files\AMD\ROCm\5.7\bin`
* Restart your system.
* Open a cmd prompt. Easiest way to do this is, in Windows Explorer go to the folder or drive you want to install this app to, in the address bar type "cmd" and press enter.
* **DON'T INSTALL** into your user directory or inside Windows or Program Files directories. Best option just go to `C:\` or `D:\` if you have other drives and open cmd there.
* Copy these commands one by one and press enter after each one:
## [comfy-cli](https://docs.comfy.org/comfy-cli/getting-started)
You can install and start ComfyUI using comfy-cli:
```bash
git clone https://github.com/patientx/ComfyUI-Zluda
pip install comfy-cli
comfy install
```
```bash
cd ComfyUI-Zluda
## Manual Install (Windows, Linux)
Python 3.14 works but you may encounter issues with the torch compile node. The free threaded variant is still missing some dependencies.
Python 3.13 is very well supported. If you have trouble with some custom node dependencies on 3.13 you can try 3.12
### 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/rocm6.4```
This is the command to install the nightly with ROCm 7.0 which might have some performance improvements:
```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.0```
### AMD GPUs (Experimental: Windows and Linux), RDNA 3, 3.5 and 4 only.
These have less hardware support than the builds above but they work on windows. You also need to install the pytorch version specific to your hardware.
RDNA 3 (RX 7000 series):
```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx110X-dgpu/```
RDNA 3.5 (Strix halo/Ryzen AI Max+ 365):
```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx1151/```
RDNA 4 (RX 9000 series):
```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/```
### 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](https://pytorch.org/docs/main/notes/get_start_xpu.html)
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/cu130```
#### 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 or M2) with any recent macOS version.
1. Install pytorch nightly. For instructions, read the [Accelerated PyTorch training on Mac](https://developer.apple.com/metal/pytorch/) Apple Developer guide (make sure to install the latest pytorch nightly).
1. Follow the [ComfyUI manual installation](#manual-install-windows-linux) instructions for Windows and Linux.
1. Install the ComfyUI [dependencies](#dependencies). If you have another Stable Diffusion UI [you might be able to reuse the dependencies](#i-already-have-another-ui-for-stable-diffusion-installed-do-i-really-have-to-install-all-of-these-dependencies).
1. 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](#manual-install-windows-linux).
#### Ascend NPUs
For models compatible with Ascend Extension for PyTorch (torch_npu). To get started, ensure your environment meets the prerequisites outlined on the [installation](https://ascend.github.io/docs/sources/ascend/quick_install.html) 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](https://ascend.github.io/docs/sources/pytorch/install.html#pytorch) page.
4. Finally, adhere to the [ComfyUI manual installation](#manual-install-windows-linux) 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](https://www.cambricon.com/docs/sdk_1.15.0/cntoolkit_3.7.2/cntoolkit_install_3.7.2/index.html)
2. Next, install the PyTorch(torch_mlu) following the instructions on the [Installation](https://www.cambricon.com/docs/sdk_1.15.0/cambricon_pytorch_1.17.0/user_guide_1.9/index.html)
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](https://support.iluvatar.com/#/DocumentCentre?id=1&nameCenter=2&productId=520117912052801536)
2. Launch ComfyUI by running `python main.py`
# 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 enable experimental memory efficient attention on recent pytorch in ComfyUI on some AMD GPUs using this command, it should already be enabled by default on RDNA3. If this improves speed for you on latest pytorch on your GPU please report it so that I can enable it by default.
```TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 python main.py --use-pytorch-cross-attention```
You can also 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](https://github.com/madebyollin/taesd), download the [taesd_decoder.pth, taesdxl_decoder.pth, taesd3_decoder.pth and taef1_decoder.pth](https://github.com/madebyollin/taesd/) 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](https://github.com/alexisrolland/docker-openssl) or one of the [3rd party binary distributions](https://wiki.openssl.org/index.php/Binaries) to run the command example above.
<br/><br/>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](https://comfy.org/discord): Try the #help or #feedback channels.
[Matrix space: #comfyui_space:matrix.org](https://app.element.io/#/room/%23comfyui_space%3Amatrix.org) (it's like discord but open source).
See also: [https://www.comfy.org/](https://www.comfy.org/)
## Frontend Development
As of August 15, 2024, we have transitioned to a new frontend, which is now hosted in a separate repository: [ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend). This repository now hosts the compiled JS (from TS/Vue) under the `web/` directory.
### Reporting Issues and Requesting Features
For any bugs, issues, or feature requests related to the frontend, please use the [ComfyUI Frontend repository](https://github.com/Comfy-Org/ComfyUI_frontend). 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/ComfyUI_frontend@1.2.2
```
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.
### Accessing the Legacy Frontend
If you need to use the legacy frontend for any reason, you can access it using the following command line argument:
```
--front-end-version Comfy-Org/ComfyUI_legacy_frontend@latest
```
```bash
install-for-older-amd.bat
```
This will use a snapshot of the legacy frontend preserved in the [ComfyUI Legacy Frontend repository](https://github.com/Comfy-Org/ComfyUI_legacy_frontend).
* If you have done every previous step correctly, it will install without errors and start ComfyUI-ZLUDA for the first time. If you already have checkpoints copy them into `models/checkpoints` folder so you can use them with ComfyUI's default workflow.
# QA
* The first generation will take longer than usual, ZLUDA is compiling for your GPU, it does this once for every new model type. This is necessary and unavoidable.
### Which GPU should I buy for this?
* You can use `comfyui.bat` or put a shortcut of it on your desktop, to run the app later. My recommendation is make a copy of `comfyui.bat` with another name maybe and modify that copy so when updating you won't get into trouble.
</details>
<details>
<summary><strong>For GPU's below 6800 (VEGA, RX 5000 and remaining 6000's; 6700, 6600 etc)</strong></summary>
* **IMPORTANT**: With this install method you MUST make sure you have the latest GPU drivers (specifically you need drivers above 25.5.1)
* **UPDATE** : There are now new libraries for "some of" these gpu's namely these listed below for HIP 6.4.2 BUT they are not tested and some of those probably won't work with the newer triton-miopen stuff so if you want you can try using the 6.4.2 route with those new libraries AND if you are updating from 6.2.4 to 6.4.2 please remember to uninstall hip 6.2.4 THEN delete the rocm folder inside program files otherwise even after uninstall the addon's added files would remain there and may cause problems.
* AMD Radeon RX 5700 XT (gfx1010) , AMD Radeon Pro V540 (gfx1011) , AMD Radeon RX 5500 XT (gfx1012)
* AMD Radeon RX 6700, AMD Radeon RX 6700 XT (gfx1031) , AMD Radeon RX 6600, AMD Radeon RX 6600 XT (gfx1032)
* AMD Radeon RX 6500, 6500XT, 6500M, 6400, 6300, 6450, W6400 (gfx1034)
* AMD Radeon 680M, AMD Radeon 660M (gfx1035)
* AMD Radeon Graphics 128SP (All 7000 series IGP Variants) (gfx1036)
* AMD Radeon 780M , AMD Ryzen Z1 ,AMD Radeon 740M (gfx1103)
* But they are not all tested and even if they work with 6.4.2 they might not work with triton-miopen stuff, in that case use legacy installer instead.
* [There is the legacy installer method still available with `install-legacy.bat` (this is the old "install.bat") which doesn't include miopen-triton stuff, but I strongly recommend them now we have solved most of the problems with them.So if you want you can still install hip 5.7.1 and use the libraries for your gpu for hip 5.7.1 or 6.2.4 and you don't need to install miopen stuff. You can use the `install-legacy.bat` but first try the install-n.bat if you have problems than go back to the legacy one.]
* Install HIP SDK 6.2.4 from [AMD ROCm Hub](https://www.amd.com/en/developer/resources/rocm-hub/hip-sdk.html) - "Windows 10 & 11 6.2.4 HIP SDK"
* Make sure the system variables `HIP_PATH` and `HIP_PATH_62` exist, both should have this value: `C:\Program Files\AMD\ROCm\6.2\`
* Also check the system path defining variable called "Path". Double-click it and click "New", then add: `C:\Program Files\AMD\ROCm\6.2\bin`
* Download this addon package from [Google Drive](https://drive.google.com/file/d/1Gvg3hxNEj2Vsd2nQgwadrUEY6dYXy0H9/view?usp=sharing) (or [alternative source](https://www.mediafire.com/file/ooawc9s34sazerr/HIP-SDK-extension(zluda395).zip/file))
* Extract the addon package into `C:\Program Files\AMD\ROCm\6.2` overwriting files if asked
* Get library files for your GPU from [likelovewant Repository](https://github.com/likelovewant/ROCmLibs-for-gfx1103-AMD780M-APU/releases/tag/v0.6.2.4) (for HIP 6.2.4)
* Go to folder `C:\Program Files\AMD\ROCm\6.2\bin\rocblas`, there should be a "library" folder. **Backup the files inside to somewhere else.**
* Open your downloaded optimized library archive and put them inside the library folder (overwriting if necessary): `C:\Program Files\AMD\ROCm\6.2\bin\rocblas\library`
* If there's a `rocblas.dll` file in the archive, copy it inside `C:\Program Files\AMD\ROCm\6.2\bin`
* Install [Visual Studio Build Tools](https://aka.ms/vs/17/release/vs_BuildTools.exe)
* **Restart your system**
* Open a command prompt. Easiest way: in Windows Explorer, go to the folder or drive where you want to install this app, in the address bar type "cmd" and press enter
* **DON'T INSTALL** into your user directory or inside Windows or Program Files directories. Best option is to go to `C:\` or `D:\` (if you have other drives) and open cmd there.
* Copy these commands one by one and press enter after each:
```bash
git clone https://github.com/patientx/ComfyUI-Zluda
```
```bash
cd ComfyUI-Zluda
```
```bash
install-n.bat
```
* If you have done every previous step correctly, it will install without errors and start ComfyUI-ZLUDA for the first time. If you already have checkpoints, copy them into `models/checkpoints` folder so you can use them with ComfyUI's default workflow.
* The first generation will take longer than usual, ZLUDA is compiling for your GPU. It does this once for every new model type. This is necessary and unavoidable.
* You can use `comfyui-n.bat` or put a shortcut of it on your desktop to run the app later. My recommendation is to make a copy of `comfyui-n.bat` with another name and modify that copy so when updating you won't get into trouble.
</details>
<details>
<summary><strong>For GPU's above 6800 (6800, 6800XT, other 6000s above & 7000s and 9000s)</strong></summary>
* **IMPORTANT**: With this install method you MUST make sure you have the latest GPU drivers (specifically you need drivers above 25.5.1)
* **UPDATE** : There are now new libraries for "some of" the unsupported gpu's from previous generations namely these listed below for HIP 6.4.2 BUT they are not tested and some of those probably won't work with the newer triton-miopen stuff so if you want you can try using the 6.4.2 route with those new libraries AND if you are updating from 6.2.4 to 6.4.2 please remember to uninstall hip 6.2.4 THEN delete the rocm folder inside program files otherwise even after uninstall the addon's added files would remain there and may cause problems.
* AMD Radeon RX 5700 XT (gfx1010) , AMD Radeon Pro V540 (gfx1011) , AMD Radeon RX 5500 XT (gfx1012)
* AMD Radeon RX 6700, AMD Radeon RX 6700 XT (gfx1031) , AMD Radeon RX 6600, AMD Radeon RX 6600 XT (gfx1032)
* AMD Radeon RX 6500, 6500XT, 6500M, 6400, 6300, 6450, W6400 (gfx1034)
* AMD Radeon 680M, AMD Radeon 660M (gfx1035)
* AMD Radeon Graphics 128SP (All 7000 series IGP Variants) (gfx1036)
* AMD Radeon 780M , AMD Ryzen Z1 ,AMD Radeon 740M (gfx1103)
* The libraries for these can be had here : [6.4.2 Libraries for unsupported GPU's](https://github.com/likelovewant/ROCmLibs-for-gfx1103-AMD780M-APU/releases/tag/v0.6.4.2)
* But they are not all tested and even if they work with 6.4.2 they might not work with triton-miopen stuff, in that case use legacy installer instead.
* Install HIP SDK 6.4.2 from [AMD ROCm Hub](https://www.amd.com/en/developer/resources/rocm-hub/hip-sdk.html) - "Windows 10 & 11 6.4.2 HIP SDK"
* Make sure the system variables `HIP_PATH` and `HIP_PATH_64` exist, both should have this value: `C:\Program Files\AMD\ROCm\6.4\`
* Also check the system path defining variable called "Path". Double-click it and click "New", then add: `C:\Program Files\AMD\ROCm\6.4\bin`
* FOR THE UNSUPPORTED GPU'S THAT HAS LIBRARIES ; DO THESE :
* Get library files for your GPU from [6.4.2 Libraries for unsupported GPU's](https://github.com/likelovewant/ROCmLibs-for-gfx1103-AMD780M-APU/releases/tag/v0.6.4.2) (for HIP 6.4.2)
* Go to folder `C:\Program Files\AMD\ROCm\6.4\bin\rocblas`, there should be a "library" folder. **Backup the files inside to somewhere else.**
* Open your downloaded optimized library archive and put them inside the library folder (overwriting if necessary): `C:\Program Files\AMD\ROCm\6.4\bin\rocblas\library`
* If there's a `rocblas.dll` file in the archive, copy it inside `C:\Program Files\AMD\ROCm\6.4\bin`
* Install [Visual Studio Build Tools](https://aka.ms/vs/17/release/vs_BuildTools.exe)
* **Restart your system**
* Open a command prompt. Easiest way: in Windows Explorer, go to the folder or drive where you want to install this app, in the address bar type "cmd" and press enter
* **DON'T INSTALL** into your user directory or inside Windows or Program Files directories. Best option is to go to `C:\` or `D:\` (if you have other drives) and open cmd there.
* Copy these commands one by one and press enter after each:
```bash
git clone https://github.com/patientx/ComfyUI-Zluda
```
```bash
cd ComfyUI-Zluda
```
```bash
install-n.bat
```
* If you have done every previous step correctly, it will install without errors and start ComfyUI-ZLUDA for the first time. If you already have checkpoints, copy them into `models/checkpoints` folder so you can use them with ComfyUI's default workflow.
* The first generation will take longer than usual, ZLUDA is compiling for your GPU. It does this once for every new model type. This is necessary and unavoidable.
* You can use `comfyui-n.bat` or put a shortcut of it on your desktop to run the app later. My recommendation is to make a copy of `comfyui-n.bat` with another name and modify that copy so when updating you won't get into trouble.
</details>
> [!IMPORTANT]
> 📢 ***REGARDING KEEPING THE APP UP TO DATE***
>
> Avoid using the update function from the manager, instead use `git pull`, which we
> are doing on every start if `comfyui.bat` or `comfyui-n.bat`is used.
>
> Only use comfy manager to update the extensions
> (Manager -> Custom Nodes Manager -> Set Filter To Installed -> Click Check Update On The Bottom Of The Window)
> otherwise it breaks the basic installation, and in that case run the install once again.
## Troubleshooting
- If you are getting `RuntimeError: GET was unable to find an engine to execute this computation` or `RuntimeError: FIND was unable to find an engine to execute this computation` in the vae decoding stage, please use CFZ CUDNN Toggle node between ksampler latent and vae decoding. And leave the enable_cudnn setting "False" , this persists until you close the comfyui from the commandline for the rest of that run. So you won't see this error again.
<img width="667" height="350" alt="Screenshot 2025-08-25 123335" src="https://github.com/user-attachments/assets/db56d460-34aa-4fda-94e2-f0bae7162691" />
That node can actually be used between conditioning or image loading etc so it's not only usable between latent and vae decoding , also you can use it in a simple workflow that it makes the setting disabled , than you can use any other workflow for the rest of the instance without worry. (try running the [1step-cudnn-disabler-workflow](https://github.com/patientx/ComfyUI-Zluda/blob/master/cfz/workflows/1step-cudnn-disabler-workflow.json) in cfz folder once after you start comfyui-zluda, it can use any sd15 or sdxl model it would just generate 1 step image than preview it so no saving) after that workflow runs once, switch to any workflow or start a new one.
- Problems with triton , try this : Remove visual studio 2022 (if you have already installed it and getting errors) and install "https://aka.ms/vs/17/release/vs_BuildTools.exe" , and then use "Developer Command Prompt" to run comfyui. This option shouldn't be needed for many but nevertheless try.
- `RuntimeError: CUDNN_BACKEND_OPERATIONGRAPH_DESCRIPTOR: cudnnFinalize FailedmiopenStatusInternalError cudnn_status: miopenStatusUnknownError` , if this is encountered at the end, while vae-decoding, use tiled-vae decoding either from official comfy nodes or from Tiled-Diffussion (my preference). Also vae-decoding is overall better with tiled-vae decoding.
- DO NOT use non-english characters as folder names to put comfyui-zluda under.
- Wipe your pip cache "C:\Users\USERNAME\AppData\Local\pip\cache" You can also do this when venv is active with : `pip cache purge`
- `xformers` isn't usable with zluda so any nodes / packages that require it doesn't work.
- Have the latest drivers installed for your amd gpu. **Also, Remove Any Nvidia Drivers** you might have from previous nvidia gpu's.
- If for some reason you can't solve with these and want to start from zero, delete "venv" folder and re-run the whole setup again step by step.
- If you can't git pull to the latest version, run these commands, `git fetch --all` and then `git reset --hard origin/master` now you can git pull
- Problems with `caffe2_nvrtc.dll`: if you are sure you properly installed hip and can see it on path, please DON'T use
python from windows store, use the link provided or 3.11 from the official website. After uninstalling python from
windows store and installing the one from the website, be sure the delete venv folder, and run install.bat once again.
- If you have an integrated GPU by AMD (e.g. AMD Radeon(TM) Graphics) you need to add `HIP_VISIBLE_DEVICES=1` to your environment variables. Other possible variables to use :
`ROCR_VISIBLE_DEVICES=1` `HCC_AMDGPU_TARGET=1` . This basically tells it to use 1st gpu -this number could be different if you have multiple gpu's-
Otherwise it will default to using your iGPU, which will most likely not work. This behavior is caused by a bug in the ROCm-driver.
- Lots of other problems were encountered and solved by users so check the issues if you can't find your problem here.
## Credits
- [ComfyUI](https://github.com/comfyanonymous/ComfyUI)
- [Zluda Wiki from SdNext](https://github.com/vladmandic/sdnext/wiki/ZLUDA)
- [Brknsoul for Rocm Libraries](https://github.com/brknsoul/ROCmLibs)
- [likelovewant for Rocm Libraries](https://github.com/likelovewant/ROCmLibs-for-gfx1103-AMD780M-APU/releases/tag/v0.6.2.4)
- [Lshqqytiger](https://github.com/lshqqytiger/ZLUDA)
- [LeagueRaINi](https://github.com/LeagueRaINi/ComfyUI)
- [ComfyUI-Manager](https://github.com/ltdrdata/ComfyUI-Manager)
[See this page for some recommendations](https://github.com/comfyanonymous/ComfyUI/wiki/Which-GPU-should-I-buy-for-ComfyUI)