Improve model card with metadata and links (#1)
Browse files- Improve model card with metadata and links (102d328e48f183e103f86c5f3003fd5c73c8a978)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
|
@@ -1,12 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# VIRES_VAE model card
|
| 2 |
|
| 3 |
**Model Page**: [VIRES](https://hjzheng.net/projects/VIRES/)
|
| 4 |
|
| 5 |
-
This is a component of VIRES model.
|
|
|
|
| 6 |
|
| 7 |
### Usage
|
| 8 |
|
| 9 |
-
Ref to our GitHub page: https://github.com/suimuc/VIRES/
|
| 10 |
|
| 11 |
## Citation
|
| 12 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-to-video
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
license: mit
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
# VIRES_VAE model card
|
| 8 |
|
| 9 |
**Model Page**: [VIRES](https://hjzheng.net/projects/VIRES/)
|
| 10 |
|
| 11 |
+
This is a component of the VIRES model, as presented in [VIRES: Video Instance Repainting with Sketch and Text Guidance](https://huggingface.co/papers/2411.16199). VIRES is a video instance repainting method with sketch and text guidance, enabling video instance repainting, replacement, generation, and removal. It leverages the generative priors of text-to-video models to maintain temporal consistency and produce visually pleasing results.
|
| 12 |
+
|
| 13 |
|
| 14 |
### Usage
|
| 15 |
|
| 16 |
+
Ref to our GitHub page: [https://github.com/suimuc/VIRES/](https://github.com/suimuc/VIRES/)
|
| 17 |
|
| 18 |
## Citation
|
| 19 |
|