说明文档

Locomotion - Onnx DirectML 优化版

Amuse

https://www.amuse-ai.com/

示例

<div align="center"> <table width="80%"> <tr class="image-row"> <td style="width: 50%; height: 50px; text-align: center;"> <video controls> <source src="https://huggingface.co/TensorStack/Locomotion-amuse/resolve/main/Sample.webm" type="video/webm"> </video> </td> <td style="width: 50%; height: 50px; text-align: center;"> <video controls> <source src="https://huggingface.co/TensorStack/Locomotion-amuse/resolve/main/Sample2.webm" type="video/webm"> </video> </td> </tr> <tr class="text-row"> <th>一只可爱的柯基在公园里开心地玩耍。</th> <th>一只可爱的浣熊在海滩上弹吉他。</th> </tr> <tr class="image-row"> <td style="width: 50%; height: 50px; text-align: center;"> <video controls> <source src="https://huggingface.co/TensorStack/Locomotion-amuse/resolve/main/Sample3.webm" type="video/webm"> </video> </td> <td style="width: 50%; height: 50px; text-align: center;"> <video controls> <source src="https://huggingface.co/TensorStack/Locomotion-amuse/resolve/main/Sample4.webm" type="video/webm"> </video> </td> </tr> <tr class="text-row"> <th>黎明时分宁静的海滩，海浪轻轻拍打。</th> <th>纽约雨夜的黑白街头摄影，湿润路面上的倒影</th> </tr> </table> </div>

致谢

感谢以下仓库的开发者，他们的工作对于实现 TextToVideo 在 ONNX 上运行至关重要：

TensorStack/Locomotion-amuse

作者 TensorStack

text-to-video

↓ 0 ♥ 2

创建时间: 2025-03-07 17:43:43+00:00

更新时间: 2025-04-01 01:35:54+00:00

在 Hugging Face 上查看

文件 (24)

.gitattributes

Icon.png

README.md

Sample.mp4

Sample.webm

Sample2.mp4

Sample2.webm

Sample3.mp4

Sample3.webm

Sample4.mp4

Sample4.webm

amuse_template.json

controlnet/model.onnx ONNX

controlnet/model.onnx.data

flow_estimation/model.onnx ONNX

resample/model.onnx ONNX

text_encoder/model.onnx ONNX

tokenizer/merges.txt

tokenizer/special_tokens_map.json

tokenizer/vocab.json

unet/model.onnx ONNX

unet/model.onnx.data

vae_decoder/model.onnx ONNX

vae_encoder/model.onnx ONNX