Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,16 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
In this work, we present **AMD Hummingbird-XT**, an efficient **DiT-based** video generative model designed for high-quality video generation on client-grade GPUs with **5B parameters** .
|
| 5 |
|
| 6 |
Hummingbird-XT is trained based on Wan2.2-5B-TI2V using **DMD step distillation** with carefully designed **data curation**, enabling **3-step generation** while preserving high visual fidelity and motion quality. To reduce the computational overhead of high-resolution video decoding in 3D convolution–based VAE decoders, we introduce a **lightweight and efficient VAE decoder** by replacing part of the 3D convolutions with depthwise separable convolutions. Additionally, to further extend the length of generated videos, we introduce **Hummingbird-XTX**, an efficient **autoregressive model** for **long-video generation** based on Wan-2.1-1.3B, which is capable of generating long videos.
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
<p align="center"><h1 align="center">
|
| 5 |
+
Bridging the Last Mile: Deploying Hummingbird-XT for Efficient Video Generation on AMD Consumer-Grade Platforms
|
| 6 |
+
</h1>
|
| 7 |
+
</p>
|
| 8 |
+
|
| 9 |
+
<p align="center">
|
| 10 |
+
<h3 align="center"><a href="https://rocm.blogs.amd.com/artificial-intelligence/hummingbirdxt/README.html">Blog</a> | <a href="https://github.com/AMD-AGI/HummingbirdXT">Code</a></h3>
|
| 11 |
+
</p>
|
| 12 |
+
|
| 13 |
+
|
| 14 |
In this work, we present **AMD Hummingbird-XT**, an efficient **DiT-based** video generative model designed for high-quality video generation on client-grade GPUs with **5B parameters** .
|
| 15 |
|
| 16 |
Hummingbird-XT is trained based on Wan2.2-5B-TI2V using **DMD step distillation** with carefully designed **data curation**, enabling **3-step generation** while preserving high visual fidelity and motion quality. To reduce the computational overhead of high-resolution video decoding in 3D convolution–based VAE decoders, we introduce a **lightweight and efficient VAE decoder** by replacing part of the 3D convolutions with depthwise separable convolutions. Additionally, to further extend the length of generated videos, we introduce **Hummingbird-XTX**, an efficient **autoregressive model** for **long-video generation** based on Wan-2.1-1.3B, which is capable of generating long videos.
|