Spaces:
Running
Running
Update constants.py
Browse files- constants.py +35 -2
constants.py
CHANGED
@@ -225,7 +225,7 @@ COLUMN_NAMES_I2V = MODEL_INFO_TAB_I2V + I2V_TAB
|
|
225 |
LEADERBORAD_INTRODUCTION = """# VBench Leaderboard
|
226 |
|
227 |
*"Which Video Generation Model is better?"*
|
228 |
-
π Welcome to the leaderboard of the **VBench**! π¦ *A Comprehensive Benchmark Suite for Video Generative Models* (**CVPR 2024
|
229 |
<div style="display: flex; flex-wrap: wrap; align-items: center; gap: 10px;">
|
230 |
<a href='https://arxiv.org/abs/2311.17982'><img src='https://img.shields.io/badge/cs.CV-Paper-b31b1b?logo=arxiv&logoColor=red'></a>
|
231 |
<a href='https://vchitect.github.io/VBench-project/'><img src='https://img.shields.io/badge/VBench-Website-green?logo=googlechrome&logoColor=green'></a>
|
@@ -238,13 +238,35 @@ LEADERBORAD_INTRODUCTION = """# VBench Leaderboard
|
|
238 |
- **Human Alignment:** We conducted extensive experiments and human annotations to validate robustness of VBench.
|
239 |
- **Valuable Insights:** VBench provides multi-perspective insights useful for the community.
|
240 |
|
241 |
-
**Join Leaderboard**: Please see the [instructions](https://github.com/Vchitect/VBench/
|
242 |
|
243 |
**Model Information**: What are the details of these Video Generation Models? See [HERE](https://github.com/Vchitect/VBench/tree/master/sampled_videos#what-are-the-details-of-the-video-generation-models)
|
244 |
|
245 |
**Credits**: This leaderboard is updated and maintained by the team of [VBench Contributors](https://github.com/Vchitect/VBench?tab=readme-ov-file#muscle-vbench-contributors).
|
246 |
"""
|
247 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
248 |
SUBMIT_INTRODUCTION = """# Submit on VBench Benchmark Introduction
|
249 |
|
250 |
## π
|
@@ -256,6 +278,17 @@ SUBMIT_INTRODUCTION = """# Submit on VBench Benchmark Introduction
|
|
256 |
β οΈ Submissions that do not correctly fill in the model name and model link may be deleted by the VBench team. The contact information you filled in will not be made public.
|
257 |
"""
|
258 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
259 |
TABLE_INTRODUCTION = """
|
260 |
"""
|
261 |
|
|
|
225 |
LEADERBORAD_INTRODUCTION = """# VBench Leaderboard
|
226 |
|
227 |
*"Which Video Generation Model is better?"*
|
228 |
+
π Welcome to the leaderboard of the **VBench**! π¦ *A Comprehensive Benchmark Suite for Video Generative Models* (**CVPR 2024 Highlight**) [](https://github.com/Vchitect/VBench)
|
229 |
<div style="display: flex; flex-wrap: wrap; align-items: center; gap: 10px;">
|
230 |
<a href='https://arxiv.org/abs/2311.17982'><img src='https://img.shields.io/badge/cs.CV-Paper-b31b1b?logo=arxiv&logoColor=red'></a>
|
231 |
<a href='https://vchitect.github.io/VBench-project/'><img src='https://img.shields.io/badge/VBench-Website-green?logo=googlechrome&logoColor=green'></a>
|
|
|
238 |
- **Human Alignment:** We conducted extensive experiments and human annotations to validate robustness of VBench.
|
239 |
- **Valuable Insights:** VBench provides multi-perspective insights useful for the community.
|
240 |
|
241 |
+
**Join Leaderboard**: Please see the [instructions](https://github.com/Vchitect/VBench/blob/master/README-FAQ.md#faq) for 3 options to participate. One option is to follow [VBench Usage info](https://github.com/Vchitect/VBench?tab=readme-ov-file#usage), and upload the generated `result.json` file here. After clicking the `Submit here!` button, click the `Refresh` button.
|
242 |
|
243 |
**Model Information**: What are the details of these Video Generation Models? See [HERE](https://github.com/Vchitect/VBench/tree/master/sampled_videos#what-are-the-details-of-the-video-generation-models)
|
244 |
|
245 |
**Credits**: This leaderboard is updated and maintained by the team of [VBench Contributors](https://github.com/Vchitect/VBench?tab=readme-ov-file#muscle-vbench-contributors).
|
246 |
"""
|
247 |
|
248 |
+
LEADERBORAD_INTRODUCTION2 = """# VBench-2.0 Leaderboard
|
249 |
+
|
250 |
+
*"Which Video Generation Model is better?"*
|
251 |
+
π Welcome to the leaderboard of the **VBench-2.0**! π¦ *Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness* [](https://github.com/Vchitect/VBench/tree/master/VBench-2.0)
|
252 |
+
<div style="display: flex; flex-wrap: wrap; align-items: center; gap: 10px;">
|
253 |
+
<a href='https://arxiv.org/abs/2503.21755'><img src='https://img.shields.io/badge/cs.CV-Paper-b31b1b?logo=arxiv&logoColor=red'></a>
|
254 |
+
<a href='https://vchitect.github.io/VBench-2.0-project/'><img src='https://img.shields.io/badge/VBench-Website-green?logo=googlechrome&logoColor=green'></a>
|
255 |
+
<a href='https://www.youtube.com/watch?v=kJrzKy9tgAc'><img src='https://img.shields.io/badge/YouTube-Video-c4302b?logo=youtube&logoColor=red'></a>
|
256 |
+
<a href='https://hits.seeyoufarm.com'><img src='https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2FVchitect%2FVBench&count_bg=%23FFA500&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=visitors&edge_flat=false'></a>
|
257 |
+
</div>
|
258 |
+
|
259 |
+
- **Comprehensive Dimensions:** We carefully decompose video generation quality into 18 comprehensive dimensions to reveal individual model's strengths and weaknesses.
|
260 |
+
- **Human Alignment:** We conducted extensive experiments and human annotations to validate robustness of VBench.
|
261 |
+
- **Valuable Insights:** VBench-2.0 provides multi-perspective insights useful for the community.
|
262 |
+
|
263 |
+
**Join Leaderboard**: Please see the [instructions](https://github.com/Vchitect/VBench/blob/master/VBench-2.0/README-FAQ.md#faq) for 3 options to participate. One option is to follow [VBench Usage info](https://github.com/Vchitect/VBench/tree/master/VBench-2.0#usage), and upload the generated `result.json` file here. After clicking the `Submit here!` button, click the `Refresh` button.
|
264 |
+
|
265 |
+
**Model Information**: What are the details of these Video Generation Models? See [HERE](https://github.com/Vchitect/VBench/tree/master/VBench-2.0/sampled_videos#what-are-the-details-of-the-video-generation-models)
|
266 |
+
|
267 |
+
**Credits**: This leaderboard is updated and maintained by the team of [VBench Contributors](https://github.com/Vchitect/VBench?tab=readme-ov-file#muscle-vbench-contributors).
|
268 |
+
"""
|
269 |
+
|
270 |
SUBMIT_INTRODUCTION = """# Submit on VBench Benchmark Introduction
|
271 |
|
272 |
## π
|
|
|
278 |
β οΈ Submissions that do not correctly fill in the model name and model link may be deleted by the VBench team. The contact information you filled in will not be made public.
|
279 |
"""
|
280 |
|
281 |
+
SUBMIT_INTRODUCTION2 = """# Submit on VBench-2.0 Benchmark Introduction
|
282 |
+
|
283 |
+
## π
|
284 |
+
1. Please note that you need to obtain the file `evaluation_results/*.json` or `evaluation_results/dimension/*.json` by running VBench-2.0 in Github. You may conduct an [Offline Check](https://github.com/Vchitect/VBench?tab=readme-ov-file#get-final-score-and-submit-to-leaderboard) before uploading.
|
285 |
+
2. Then, pack these JSON files into a `ZIP` archive, ensuring that the top-level directory of the ZIP contains the individual JSON files.
|
286 |
+
3. Finally, upload the ZIP archive below.
|
287 |
+
|
288 |
+
β οΈ Uploading generated videos or images of the model is invalid!
|
289 |
+
β οΈ Submissions that do not correctly fill in the model name and model link may be deleted by the VBench team. The contact information you filled in will not be made public.
|
290 |
+
"""
|
291 |
+
|
292 |
TABLE_INTRODUCTION = """
|
293 |
"""
|
294 |
|