Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 23 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,29 @@ Note that running `update.bat` is important, otherwise you may be using a previo

Note that the models will be downloaded automatically. You will download more than 30GB from HuggingFace.


**Windows WSL2**:
#W11->WSL2->Ubuntu 24.04 LTS

conda create --name FramePack python=3.10
conda activate FramePack
cd /home/youruserORcreatenewfolder/ #IMPORTANT FOR WSL2 MOVE OUT OF YOUR /MNT/C/USERS/USERNAME. Use internal filesystem instead(VHD). Disk transfer speed increased from 30MB/s -> 700MB/s and it/s 700 to 15 after this change.
git clone https://github.com/lllyasviel/FramePack.git
cd FramePack
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
pip install -r requirements.txt

Optional:

pip install sageattention
pip install flash-attn --no-deps
pip install --no-cache-dir xformers --index-url https://download.pytorch.org/whl/cu126 -f https://download.pytorch.org/whl/torch_stable.html

To start the GUI, run:

python demo_gradio.py


**Linux**:

We recommend having an independent Python 3.10.
Expand Down