Diffusers
Safetensors
OrbitQuantComponentArtifact
orbitquant
quantized
diffusion-transformer
8-bit precision
Instructions to use WaveCut/Wan2.1-T2V-1.3B-Diffusers-OrbitQuant-W4A4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/Wan2.1-T2V-1.3B-Diffusers-OrbitQuant-W4A4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/Wan2.1-T2V-1.3B-Diffusers-OrbitQuant-W4A4", 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
Refresh OrbitQuant runtime usage examples
Browse files- README.md +1 -0
- SHA256SUMS +1 -1
README.md
CHANGED
|
@@ -37,6 +37,7 @@ pipe = load_quantized_pipeline_from_artifact(
|
|
| 37 |
artifact_dir,
|
| 38 |
torch_dtype=torch.bfloat16,
|
| 39 |
device="cuda",
|
|
|
|
| 40 |
)
|
| 41 |
|
| 42 |
frames = pipe(
|
|
|
|
| 37 |
artifact_dir,
|
| 38 |
torch_dtype=torch.bfloat16,
|
| 39 |
device="cuda",
|
| 40 |
+
runtime_mode="auto_fused",
|
| 41 |
)
|
| 42 |
|
| 43 |
frames = pipe(
|
SHA256SUMS
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
|
| 2 |
c7d0a00ee273efd217df7a3d4c38aae28065af27a6d9179d8b8cbfae762f2551 assets/video_generation_comparison_matrix.webp
|
| 3 |
ccf87334e02eee391e4ced63f056c1cc5efeb2ec4d32a7050ab089463e8bc1cd benchmark/summary.json
|
| 4 |
2fe65bda9f0f318516c36ac28d22f76ee645409bc220692926a4311547ca9c4a model.safetensors
|
|
|
|
| 1 |
+
ee359d164f4138fd9b47c3ba68f659e7f4455ffc73047b091dfac9412980bbc2 README.md
|
| 2 |
c7d0a00ee273efd217df7a3d4c38aae28065af27a6d9179d8b8cbfae762f2551 assets/video_generation_comparison_matrix.webp
|
| 3 |
ccf87334e02eee391e4ced63f056c1cc5efeb2ec4d32a7050ab089463e8bc1cd benchmark/summary.json
|
| 4 |
2fe65bda9f0f318516c36ac28d22f76ee645409bc220692926a4311547ca9c4a model.safetensors
|