From 4282a4c0950bb564d07050f4c75ea94183b29eb3 Mon Sep 17 00:00:00 2001 From: DeepBeepMeep Date: Wed, 26 Mar 2025 18:14:05 +0100 Subject: [PATCH] Added instructions to install on RTX 50xx --- README.md | 56 ++++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 43 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index 3fabadc..298d9aa 100644 --- a/README.md +++ b/README.md @@ -19,6 +19,7 @@ In this repository, we present **Wan2.1**, a comprehensive and open suite of vid ## 🔥 Latest News!! +* Mar 20 2025: 👋 Good news ! Official support for RTX 50xx please check the installation instructions below. * Mar 19 2025: 👋 Wan2.1GP v3.2: - Added Classifier-Free Guidance Zero Star. The video should match better the text prompt (especially with text2video) at no performance cost: many thanks to the **CFG Zero * Team:**\ Dont hesitate to give them a star if you appreciate the results: https://github.com/WeichenFan/CFG-Zero-star @@ -88,7 +89,7 @@ You will find the original Wan2.1 Video repository here: https://github.com/Wan- -## Installation Guide for Linux and Windows +## Installation Guide for Linux and Windows for GPUs up to RTX40xx **If you are looking for a one click installation, just go to the Pinokio App store : https://pinokio.computer/** @@ -109,15 +110,23 @@ pip install torch==2.6.0 torchvision torchaudio --index-url https://download.pyt # 2. Install pip dependencies pip install -r requirements.txt -# 3.1 optional Sage attention support (30% faster, easy to install on Linux but much harder on Windows) +# 3.1 optional Sage attention support (30% faster) +# Windows only: extra step only needed for windows as triton is included in pytorch with the Linux version of pytorch +pip install triton-windows +# For both Windows and Linux pip install sageattention==1.0.6 -# or for Sage Attention 2 (40% faster, sorry only manual compilation for the moment) + +# 3.2 optional Sage 2 attention support (40% faster) +# Windows only +pip install triton-windows +pip install https://github.com/woct0rdho/SageAttention/releases/download/v2.1.1-windows/sageattention-2.1.1+cu126torch2.6.0-cp310-cp310-win_amd64.whl +# Linux only (sorry only manual compilation for the moment, but is straight forward with Linux) git clone https://github.com/thu-ml/SageAttention cd SageAttention pip install -e . -# 3.2 optional Flash attention support (easy to install on Linux but much harder on Windows) +# 3.3 optional Flash attention support (easy to install on Linux but may be complex on Windows as it will try to compile the cuda kernels) pip install flash-attn==2.7.2.post1 ``` @@ -125,17 +134,38 @@ pip install flash-attn==2.7.2.post1 Note pytorch *sdpa attention* is available by default. It is worth installing *Sage attention* (albout not as simple as it sounds) because it offers a 30% speed boost over *sdpa attention* at a small quality cost. In order to install Sage, you will need to install also Triton. If Triton is installed you can turn on *Pytorch Compilation* which will give you an additional 20% speed boost and reduced VRAM consumption. -### Ready to use python wheels for Windows users -I provide here links to simplify the installation for Windows users with Python 3.10 / Pytorch 2.51 / Cuda 12.4. I won't be able to provide support neither guarantee they do what they should do. -- Triton attention (needed for *pytorch compilation* and *Sage attention*) -``` -pip install https://github.com/woct0rdho/triton-windows/releases/download/v3.2.0-windows.post9/triton-3.2.0-cp310-cp310-win_amd64.whl # triton for pytorch 2.6.0 +## Installation Guide for Linux and Windows for GPUs up to RTX50xx +RTX50XX are only supported by pytorch starting from pytorch 2.7.0 which is still in beta. Therefore this version may be less stable.\ +It is important to use Python 3.10 otherwise the pip wheels may not be compatible. ``` +# 0 Download the source and create a Python 3.10.9 environment using conda or create a venv using python +git clone https://github.com/deepbeepmeep/Wan2GP.git +cd Wan2GP +conda create -n wan2gp python=3.10.9 +conda activate wan2gp -- Sage attention -``` -pip install https://github.com/deepbeepmeep/SageAttention/raw/refs/heads/main/releases/sageattention-2.1.0-cp310-cp310-win_amd64.whl # for pytorch 2.6.0 (experimental, if it works, otherwise you you will need to install and compile manually, see above) - +# 1 Install pytorch 2.7.0: +pip install torch==2.7.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu128 + +# 2. Install pip dependencies +pip install -r requirements.txt + +# 3.1 optional Sage attention support (30% faster) +# Windows only: extra step only needed for windows as triton is included in pytorch with the Linux version of pytorch +pip install triton-windows +# For both Windows and Linux +pip install sageattention==1.0.6 + + +# 3.2 optional Sage 2 attention support (40% faster) +# Windows only +pip install triton-windows +pip install https://github.com/woct0rdho/SageAttention/releases/download/v2.1.1-windows/sageattention-2.1.1+cu128torch2.7.0-cp310-cp310-win_amd64.whl + +# Linux only (sorry only manual compilation for the moment, but is straight forward with Linux) +git clone https://github.com/thu-ml/SageAttention +cd SageAttention +pip install -e . ``` ## Run the application