Instructions to use TencentARC/CubeComposer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use TencentARC/CubeComposer with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,6 @@ language:
|
|
| 9 |
- zh
|
| 10 |
pipeline_tag: video-to-video
|
| 11 |
---
|
| 12 |
-
## CubeComposer Model
|
| 13 |
|
| 14 |
<p align="center"> <b> CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video </b> </p>
|
| 15 |
|
|
@@ -19,7 +18,17 @@ pipeline_tag: video-to-video
|
|
| 19 |
|
| 20 |
**TL;DR**: Generate one cubemap face per time window with an effective and efficient context mechanism. Then, perspective video becomes 4K 360° without the memory blow‑up or the low‑res‑then‑upscale.
|
| 21 |
|
| 22 |
-
For more details, please visit our [project page](https://lg-li.github.io/project/cubecomposer/).
|
| 23 |
|
|
|
|
| 24 |
|
|
|
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
- zh
|
| 10 |
pipeline_tag: video-to-video
|
| 11 |
---
|
|
|
|
| 12 |
|
| 13 |
<p align="center"> <b> CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video </b> </p>
|
| 14 |
|
|
|
|
| 18 |
|
| 19 |
**TL;DR**: Generate one cubemap face per time window with an effective and efficient context mechanism. Then, perspective video becomes 4K 360° without the memory blow‑up or the low‑res‑then‑upscale.
|
| 20 |
|
| 21 |
+
For more details, please visit our [project page](https://lg-li.github.io/project/cubecomposer/) and [GitHub repo](https://github.com/TencentARC/CubeComposer).
|
| 22 |
|
| 23 |
+
### Model variants
|
| 24 |
|
| 25 |
+
We provide two variants of CubeComposer in this repo:
|
| 26 |
|
| 27 |
+
- cubecomposer-3k: supports 2K/3K generation, cubemap size = 512/768, temporal window length = 9 frames.
|
| 28 |
+
- cubecomposer-4k: supports 4K generation, cubemap size = 960, temporal window length = 5 frames.
|
| 29 |
+
|
| 30 |
+
### License
|
| 31 |
+
|
| 32 |
+
This repository is released under the terms of the [LICENSE file](./LICENSE).
|
| 33 |
+
|
| 34 |
+
By cloning, downloading, using, or distributing this repository or any of its models or weights, you agree to comply with the terms and conditions specified in the LICENSE.
|