Spaces:
Running
Running
Commit History
-
p-video-2-pro (#10) Running
- p-video-2-pro added (f10b996916b1856e74454d049d181da483672be5) - cost mode added (d098394fa790617da8a7de42681dc3f5e7581700) - small fixes (3970466d6c1dcc3dd9f7fd9a11966acdbbce9b5f) - adding missing models (9856a5489c179be0bd95e2744930475f15a06e8f)2ce6670
-
Prompt samples for p-video-2 (#8)
- adding prompt samples p-video-2 (8926e7ddcc16e1af7df106a07191babc06bfbbcc)da27691
-
p-video-2 (#7)
- p-video-2 benchmarks (1903aed86d60f30cda20506942dee2160a2b55c8) - changing dataset name (d116f47d64640ae00f4bd41a5fdff4fa442536ef)8036182
-
prompt-samples (#6)
- video edit prompt samples (cc9cf93e1d03e5ece0cded717c4f2572536dc614)4699199
-
video to video (#5)
- video-to-video model (465cf7a2aca2514ff789864a1921a563bdcbc848) - small fixes based on review (925fd12f37c725a833afda08a6f0cdc5252d90e1)bedbcdc
-
new-model-mode (#4)
- adding new model mode (0ad4e9bc017167a8624cc89852342440e7adef19)6aca0c6 -
log scale (#3)
- style fixes (d5590ebceb9361133bf317e15d76897c1091d28e) - cleaning css (baa43b90710449175cd743f22621f241258c111f) - light and dark mode (1bf1b48daa446fc0f2498117fc66bf9d5844635a) - updating about page (517e6683cfecc16172b4a95611d77b4277d12254) - refactor: update about tab with experimentation details (3473c50e525da355506889d610dda53eaca89e34) - fixing mobile rendering (754a2279b6b26d1708a4d33fd8dfbfce08c54825) - changing inferbench to p-bench (0fa188200802697b6c27337446101c5d73142efe) - new ui (4b9f11d4ff35dd618331fb51b31778ed7a75bcf8) - feat: add AA and Arenaai results, fix some ui features (4527ab9a70703593fd674dca571ccbe2c9900633) - ui updates (3f9b0a536cd48fdd6062945abb5e008f6101b144) - fixing samples (335823ace0a429bbb7942bb7870a32c80c4bd959) - cleaning and updating about (a9c18ffb9ca574375a1e1431b8a3c9a911c0aff2) - adding log scale and fixing safari rendering (a8fa348f1d1ddd3931e22df2891fc56d0b375074) - Merge style/ui-update into pr/3 (6d8f26e0e086e31a95553f9076f5ecfccbafdd8b) -…1dd19c2
-
ui-updates (#1)
- style fixes (d5590ebceb9361133bf317e15d76897c1091d28e) - cleaning css (baa43b90710449175cd743f22621f241258c111f) - light and dark mode (1bf1b48daa446fc0f2498117fc66bf9d5844635a) - updating about page (517e6683cfecc16172b4a95611d77b4277d12254) - refactor: update about tab with experimentation details (3473c50e525da355506889d610dda53eaca89e34) - fixing mobile rendering (754a2279b6b26d1708a4d33fd8dfbfce08c54825) - changing inferbench to p-bench (0fa188200802697b6c27337446101c5d73142efe) - new ui (4b9f11d4ff35dd618331fb51b31778ed7a75bcf8) - feat: add AA and Arenaai results, fix some ui features (4527ab9a70703593fd674dca571ccbe2c9900633) - ui updates (3f9b0a536cd48fdd6062945abb5e008f6101b144) - fixing samples (335823ace0a429bbb7942bb7870a32c80c4bd959) - cleaning and updating about (a9c18ffb9ca574375a1e1431b8a3c9a911c0aff2) Co-authored-by: Begüm Çığ <begumcig@users.noreply.huggingface.co>e680130
-
add: p-image-2-ideogram-benchmarking-results
5fc63f1
-
feat: partially fill in the One IG results
Begüm Cig0e5bb7f
-
feat: enhance data processing in app.py to handle URL formatting and compute aggregate GenEval scores; update sorting logic for leaderboard metrics
c123568
-
chore: cleanup unnecessary code for runnign benchmark
fd08cbd