Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
-
<h1 align='center'>MTVCraft</h1>
|
| 2 |
-
<h2 align='center'>An Open Veo3-style Audio-Video Generation Demo</h2>
|
| 3 |
|
| 4 |
|
| 5 |
<table align='center' border="0" style="width: 100%; text-align: center; margin-top: 80px;">
|
|
@@ -45,13 +45,9 @@ Specifically, the framework consists of a multi-stage pipeline. First, MTVCraft
|
|
| 45 |
Notably, both Qwen3 and ElevenLabs can be replaced by available alternatives with similar capabilities.
|
| 46 |
|
| 47 |
<div align="center">
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
</div>
|
| 52 |
|
| 53 |
-
|
| 54 |
-
|
| 55 |
## ⚙️ Installation
|
| 56 |
|
| 57 |
For CUDA 12.1, you can install the dependencies with the following commands. Otherwise, you need to manually install `torch`, `torchvision` , `torchaudio` and `xformers`.
|
|
|
|
| 1 |
+
<h1 align='center' style='font-size: 3em;'>MTVCraft</h1>
|
| 2 |
+
<h2 align='center' style='font-size: 1.5em; color: grey;'>An Open Veo3-style Audio-Video Generation Demo</h2>
|
| 3 |
|
| 4 |
|
| 5 |
<table align='center' border="0" style="width: 100%; text-align: center; margin-top: 80px;">
|
|
|
|
| 45 |
Notably, both Qwen3 and ElevenLabs can be replaced by available alternatives with similar capabilities.
|
| 46 |
|
| 47 |
<div align="center">
|
| 48 |
+
<img src="https://huggingface.co/BAAI/MTVCraft/resolve/main/pipeline.png" alt="MTVCraft Pipeline" width="60%">
|
|
|
|
|
|
|
| 49 |
</div>
|
| 50 |
|
|
|
|
|
|
|
| 51 |
## ⚙️ Installation
|
| 52 |
|
| 53 |
For CUDA 12.1, you can install the dependencies with the following commands. Otherwise, you need to manually install `torch`, `torchvision` , `torchaudio` and `xformers`.
|