Instructions to use amd/HummingbirdXT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use amd/HummingbirdXT with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("amd/HummingbirdXT", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ Hummingbird-XT is trained based on Wan2.2-5B-TI2V using **DMD step distillation*
|
|
| 7 |
|
| 8 |
As a result, Hummingbird-XT achieves a **33×** speedup on Strix Halo iGPU and a **40×** speedup on AMD Instinct™ MI325, and supports generating **121-frame** videos at **720×1280** resolution across both server-grade (AMD Instinct™ MI300 and AMD Instinct™ MI325) and client-grade (Strix Halo and Navi48) devices. Quantitative results on the VBench-T2V and VBench-I2V benchmarks show that Hummingbird-XT achieves competitive performance compared to the original **Wan2.2-5B-TI2V** model.
|
| 9 |
|
| 10 |
-
The Training and inference code is fully released on
|
| 11 |
|
| 12 |
|
| 13 |
|
|
|
|
| 7 |
|
| 8 |
As a result, Hummingbird-XT achieves a **33×** speedup on Strix Halo iGPU and a **40×** speedup on AMD Instinct™ MI325, and supports generating **121-frame** videos at **720×1280** resolution across both server-grade (AMD Instinct™ MI300 and AMD Instinct™ MI325) and client-grade (Strix Halo and Navi48) devices. Quantitative results on the VBench-T2V and VBench-I2V benchmarks show that Hummingbird-XT achieves competitive performance compared to the original **Wan2.2-5B-TI2V** model.
|
| 9 |
|
| 10 |
+
The Training and inference code is fully released on [Hummingbird-XT](https://github.com/AMD-AGI/HummingbirdXT), and the technical details is released on [Bridging the Last Mile: Deploying Hummingbird-XT for Efficient Video Generation on AMD Consumer-Grade Platforms](https://rocm.blogs.amd.com/artificial-intelligence/hummingbirdxt/README.html).
|
| 11 |
|
| 12 |
|
| 13 |
|