lllyasviel / lllyasviel/FramePack
For Nvidia 50 Series (Blackwell) GPU.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
You need to install the nightly version by running:
First uninstall the old one by running:
```
pip uninstall torch
pip uninstall torchvision
pip uninstall torchaudio
```
Then install the new nightly version with blackwell support.
```bash
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128
```
Since the project is running locally on Windows, you must manually update the libraries.
Navigate to the folder:
```
C:\Users\bob\framepack_cu126_torch26\framepack_cu126_torch26\system\python\Lib\site-packages
```
Then locate the folders named `torch`, `torchvision`, and `torchaudio`.
Replace these folders with the corresponding ones from the newly installed nightly version, which should exist somewhere in your system after installation.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No repository files or tests are identified. Start by inspecting the project's Windows installation and runtime setup, then reproduce the Nvidia 50 Series case using the nightly torch, torchvision, and torchaudio commands in the issue. Done should mean FramePack runs with Blackwell support without manually replacing packages in site-packages.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100