2025/07/12

A release with latest PyTorch 2.7.1 + CUDA 12.8 and xFormers 0.0.31.post1 installed. Also with triton installed.

You need a GPU with at least Turing architecture (RTX 20 / GTX 16 series) to use this package.
For Volta, Pascal and Maxwell GPUs, use the v2 package.

Notes

1. You need to download 2 files (.7z.001 and .7z.002), then open the 001 file and extract it. You don't need to open the 002 file again.

2. If you're upgrading from the previous version, copy/move your HuggingFaceHub folder to the new one.

3. You may want to install the latest CUDA Toolkit (12.9.1) if possible. As a reminder, it's recommended to uninstall the older versions of CUDA Toolkit first, and only Libraries and Compilers are needed to install

Versions

• Python 3.12.11
• CUDA 12.8
• PyTorch 2.7.1

2025/05/29

A pre-release for Blackwell (RTX 50 series) and Ada Lovelace (RTX 40 series) GPUs with triton installed.

The usage is the same as the current README.

Notes

1. You need to download 2 files (.7z.001 and .7z.002), then open the 001 file and extract it. You don't need to open the 002 file again.

2. If you're upgrading from the previous version, copy/move your HuggingFaceHub folder to the new one.

3. You may want to install the latest CUDA Toolkit (12.9) if possible. As a reminder, it's recommended to uninstall the older versions of CUDA Toolkit first, and only Libraries and Compilers are needed to install

Versions

• Python 3.12.10
• CUDA 12.8
• PyTorch 2.7.0

2025/05/02

A pre-release for Blackwell (RTX 50 series) GPUs.

The usage is the same as the current README.

Notes

1. You need to download 2 files (.7z.001 and .7z.002), then open the 001 file and extract it. You don't need to open the 002 file again.

2. If you're upgrading from the old version, copy/move your HuggingFaceHub folder to the new one.

3. For Blackwell users, you may want to install the latest CUDA Toolkit (12.9) if possible. As a reminder, it's recommended to uninstall the older versions of CUDA Toolkit first, and only Libraries and Compilers are needed to install

Known issue(s)

• When running in MV mode, the web page will hide "MultiView Prompt" and "MultiView to 3D Gallery" by default. You need to click to show them first. This could be a Gradio compatibility issue.

Versions

• Python 3.12.10
• CUDA 12.8
• PyTorch 2.7.0

2025/03/27

README | 中文说明

Release for MV.
Major updates included, and a new updater for future major updates.

Prerequisite

• CUDA Toolkit (from 12.4 to 12.8, all fine)
• MSVC VC++ Build Tools (or Visual Studio with C++ workload)

Usage

• Download and extract.
• If you're upgrading from the old version, copy/move your HuggingFaceHub folder to the new one.
• Run 0-initialize.bat
• Run 1-compile-install-texture-gen.bat
• Run 2-download-models.bat
• Run 4-start-mv.bat
• Open http://localhost:8080/

Tip(s)

• Try add --profile 3 or --profile 2 if you have enough VRAM to spare. The default --profile 4 is only using 6GB of VRAM.

Versions

• Python 3.12.9
• CUDA 12.4
• PyTorch 2.6.0

2025/01/25

See the README for instructions.

使用方法见 中文说明 。

Versions | 版本信息

• Python 3.12.8
• CUDA 12.4
• PyTorch 2.5.1