update

arena_elo/elo_rating/elo_analysis.py

@@ -364,7 +364,7 @@ if __name__ == "__main__":
     pretty_print_elo_rating(anony_results["elo_rating_final"])
     print(f"last update : {anony_results['last_updated_datetime']}")
 
-    last_updated_tstamp = anony_results["last_updated_tstamp"]
+    last_updated_tstamp = full_results["last_updated_tstamp"]
     cutoff_date = datetime.datetime.fromtimestamp(
         last_updated_tstamp, tz=timezone("US/Pacific")
     ).strftime("%Y%m%d")

arena_elo/results/{latest/clean_battle_image_editing_20240315.json → 20240328/clean_battle_image_editing.json}

@@ -790,5 +790,101 @@
     "judge": "arena_user_::1",
     "anony": true,
     "tstamp": 1710535672.9791
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "Pix2PixZero",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711610477.1213
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "Pix2PixZero",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711629129.3894
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "CycleDiffusion",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711629705.2246
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "Pix2PixZero",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711630362.5575
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_127.0.0.1",
+    "anony": false,
+    "tstamp": 1711631112.5207
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "Prompt2prompt",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711631690.5127
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_a",
+    "judge": "arena_user_127.0.0.1",
+    "anony": false,
+    "tstamp": 1711633200.2923
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_a",
+    "judge": "arena_user_127.0.0.1",
+    "anony": false,
+    "tstamp": 1711633594.9922
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711635443.3071
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711635899.3088
+  },
+  {
+    "model_a": "SDEdit",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711639015.428
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711646372.1201
   }
 ]

arena_elo/results/20240328/elo_results_image_editing.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1430e6703dd6fc1e5b8ce06b11bb3a47516763a33edaf99e4c8547da5d9a8516
+size 57064

arena_elo/results/20240328/image_editing_leaderboard.csv

@@ -0,0 +1,8 @@
+key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
+Prompt2prompt,Prompt2prompt,1227.5508595026165,1158.5510681980204,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io
+InstructPix2Pix,InstructPix2Pix,1160.2057367236093,1071.0628993075604,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
+PNP,PNP,1142.693603173293,1165.4957550490212,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
+MagicBrush,MagicBrush,1053.1728944865915,1130.5422054860635,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush
+Pix2PixZero,Pix2PixZero,918.6047552604578,960.3217617445996,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io
+CycleDiffusion,CycleDiffusion,865.0529105743963,813.4794423328381,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion
+SDEdit,SDEdit,632.7192402790356,700.546867881897,MIT License,Stanford University,https://sde-image-editing.github.io

arena_elo/results/{latest/clean_battle_t2i_generation_20240327.json → 20240330/clean_battle_t2i_generation.json}

@@ -21982,5 +21982,973 @@
     "judge": "arena_user_::1",
     "anony": true,
     "tstamp": 1711541359.3793
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "OpenJourney",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711610623.6551
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "OpenJourney",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711610660.2674
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.6.126",
+    "anony": false,
+    "tstamp": 1711611656.6087
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "Playground v2",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711611714.5223
+  },
+  {
+    "model_a": "Playground v2",
+    "model_b": "PlayGroundV2.5",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711622208.7892
+  },
+  {
+    "model_a": "Playground v2",
+    "model_b": "PlayGroundV2.5",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711623286.6883
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "LCM",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711623414.4988
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "LCM",
+    "winner": "tie",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711623631.5554
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "SDXLTurbo",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711627110.7655
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "PixArtAlpha",
+    "winner": "tie",
+    "judge": "arena_user_10.16.6.126",
+    "anony": false,
+    "tstamp": 1711627173.8196
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "SDXLLightning",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.6.126",
+    "anony": false,
+    "tstamp": 1711627232.2276
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "Playground v2",
+    "winner": "tie",
+    "judge": "arena_user_10.16.6.126",
+    "anony": false,
+    "tstamp": 1711627811.1569
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "LCM",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711628539.518
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "Playground v2",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.6.126",
+    "anony": false,
+    "tstamp": 1711628765.1336
+  },
+  {
+    "model_a": "Playground v2",
+    "model_b": "PlayGroundV2.5",
+    "winner": "tie",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711630489.3854
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "SDXLLightning",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711638839.5102
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "LCM",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711639335.7323
+  },
+  {
+    "model_a": "Playground v2",
+    "model_b": "PlayGroundV2.5",
+    "winner": "tie",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711644182.7469
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "Playground v2",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711645743.7583
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "OpenJourney",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711673691.6253
+  },
+  {
+    "model_a": "PlayGroundV2.5",
+    "model_b": "SDXL",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.6.126",
+    "anony": false,
+    "tstamp": 1711673973.9905
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "OpenJourney",
+    "winner": "tie",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711677730.5132
+  },
+  {
+    "model_a": "PlayGroundV2.5",
+    "model_b": "PixArtAlpha",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711679088.7088
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "PlayGroundV2.5",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711679733.5804
+  },
+  {
+    "model_a": "Playground v2",
+    "model_b": "PixArtAlpha",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711680163.6801
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "SDXLTurbo",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711682347.0832
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "PixArtAlpha",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711682460.6742
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "PixArtAlpha",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711682540.8631
+  },
+  {
+    "model_a": "PlayGroundV2.5",
+    "model_b": "SDXLLightning",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.6.126",
+    "anony": false,
+    "tstamp": 1711683390.2225
+  },
+  {
+    "model_a": "Playground v2",
+    "model_b": "SDXL",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711690971.115
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "SDXLTurbo",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711691256.3373
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711694743.7244
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.6.126",
+    "anony": false,
+    "tstamp": 1711696933.1739
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "Playground v2",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711701025.1014
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711704985.0803
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "SDXLTurbo",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711705938.3612
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "PixArtAlpha",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711706003.0875
+  },
+  {
+    "model_a": "PlayGroundV2.5",
+    "model_b": "StableCascade",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711711576.083
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711715360.2608
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "OpenJourney",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711718677.0627
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "SDXLLightning",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711722531.6681
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "SDXLTurbo",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711722650.6499
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711724572.8236
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "SDXL",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711724958.2577
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "Playground v2",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711724961.0794
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "Playground v2",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711725069.4096
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "PlayGroundV2.5",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711725283.6897
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "SDXL",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711726214.992
+  },
+  {
+    "model_a": "PlayGroundV2.5",
+    "model_b": "Playground v2",
+    "winner": "model_a",
+    "judge": "arena_user_127.0.0.1",
+    "anony": false,
+    "tstamp": 1711726483.5946
+  },
+  {
+    "model_a": "PlayGroundV2.5",
+    "model_b": "Playground v2",
+    "winner": "model_a",
+    "judge": "arena_user_127.0.0.1",
+    "anony": false,
+    "tstamp": 1711726483.5946
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "StableCascade",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711727344.0479
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711727395.4847
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "PlayGroundV2.5",
+    "winner": "tie",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711727886.1271
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "Playground v2",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711728599.7983
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "LCM",
+    "winner": "tie",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711731238.6486
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711731516.6119
+  },
+  {
+    "model_a": "PlayGroundV2.5",
+    "model_b": "Playground v2",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711740379.7498
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711751661.9328
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "PixArtAlpha",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711751779.935
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "playground_PlayGroundV2_generation",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711752371.1875
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711753271.7549
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "LCM",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711753346.105
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "OpenJourney",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711753460.4018
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711753536.7618
+  },
+  {
+    "model_a": "playground_PlayGroundV2.5_generation",
+    "model_b": "SDXL",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711754464.5646
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "StableCascade",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711755252.7996
+  },
+  {
+    "model_a": "playground_PlayGroundV2_generation",
+    "model_b": "playground_PlayGroundV2.5_generation",
+    "winner": "tie",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711759220.1672
+  },
+  {
+    "model_a": "playground_PlayGroundV2.5_generation",
+    "model_b": "SDXLLightning",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711761666.7408
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "StableCascade",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711761801.7518
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "StableCascade",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711761810.2584
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711761980.2339
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711765212.7061
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "LCM",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711765374.2042
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "playground_PlayGroundV2.5_generation",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711765427.0869
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "LCM",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711765557.4506
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "PixArtAlpha",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711767954.5977
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711768815.4504
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711775186.0394
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "playground_PlayGroundV2_generation",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711779421.4325
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711779705.6008
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "PixArtAlpha",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711780036.1106
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "OpenJourney",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711780085.7628
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711780200.6405
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "LCM",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711780372.2648
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "LCM",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711780446.3475
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "LCM",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711780453.9795
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711780470.9437
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "LCM",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711780477.4437
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711780518.457
+  },
+  {
+    "model_a": "playground_PlayGroundV2.5_generation",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711780554.0623
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711780632.2754
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "playground_PlayGroundV2.5_generation",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711783186.0901
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711790134.292
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "SDXLTurbo",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711791903.2373
+  },
+  {
+    "model_a": "playground_PlayGroundV2.5_generation",
+    "model_b": "OpenJourney",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711792706.0287
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "SDXLLightning",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711795394.9764
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "playground_PlayGroundV2.5_generation",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711797214.2905
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "playground_PlayGroundV2.5_generation",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711801376.7886
+  },
+  {
+    "model_a": "playground_PlayGroundV2_generation",
+    "model_b": "OpenJourney",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711803173.8503
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "playground_PlayGroundV2_generation",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711803216.1695
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "SDXLLightning",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711803267.3012
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711803374.1367
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "playground_PlayGroundV2_generation",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711803415.276
+  },
+  {
+    "model_a": "playground_PlayGroundV2.5_generation",
+    "model_b": "LCM",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711803499.6558
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711803602.7456
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "SDXLTurbo",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711803874.6225
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711804104.561
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "SDXLLightning",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711808561.5508
+  },
+  {
+    "model_a": "StableCascade",
+    "model_b": "SDXL",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711808623.9807
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "LCM",
+    "winner": "tie",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711811551.4153
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "playground_PlayGroundV2_generation",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711811788.9179
+  },
+  {
+    "model_a": "playground_PlayGroundV2.5_generation",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711820810.9192
+  },
+  {
+    "model_a": "PixArtAlpha",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711825296.8492
+  },
+  {
+    "model_a": "SDXLTurbo",
+    "model_b": "OpenJourney",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711834913.4899
+  },
+  {
+    "model_a": "SDXL",
+    "model_b": "SDXLLightning",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711834976.5468
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "StableCascade",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711836150.0007
+  },
+  {
+    "model_a": "LCM",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.8.237",
+    "anony": false,
+    "tstamp": 1711836363.7289
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "playground_PlayGroundV2.5_generation",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711836435.8043
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "playground_PlayGroundV2_generation",
+    "winner": "tie",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711836547.9563
+  },
+  {
+    "model_a": "SDXLLightning",
+    "model_b": "OpenJourney",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711836613.3128
+  },
+  {
+    "model_a": "OpenJourney",
+    "model_b": "playground_PlayGroundV2_generation",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711836677.2201
   }
 ]

arena_elo/results/20240330/elo_results_t2i_generation.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e963f9d4b66d29c2f05a3923eff56cebd1f09b07223ac069456e08dc6143cda8
+size 66894

arena_elo/results/20240330/t2i_generation_leaderboard.csv

@@ -0,0 +1,10 @@
+key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
+Playground v2.5,Playground v2.5,1226.2872445351936,1236.5076527218755,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
+StableCascade,StableCascade,1105.3322734027522,1062.0980902577003,stable-cascade-nc-community (other),Stability AI,https://huggingface.co/stabilityai/stable-cascade
+Playground v2,Playground v2,1091.4371447234744,1087.3576445526567,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
+SDXLLightning,SDXLLightning,1043.235902888147,1019.4526672266176,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
+PixArtAlpha,PixArtAlpha,1020.6412075829058,1001.5090282446616,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
+SDXL,SDXL,964.7626495363717,969.8928133531979,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+SDXLTurbo,SDXLTurbo,912.2113859675355,914.9478831930971,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
+OpenJourney,OpenJourney,841.2224045541894,835.4563491411935,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
+LCM,LCM,794.8697868094328,812.962889153237,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7

arena_elo/results/latest/clean_battle_image_editing.json

@@ -0,0 +1,890 @@
+[
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707712630.872
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707712699.668
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "MagicBrush",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707712896.0427
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707712929.7061
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707713147.0445
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "PNP",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707713198.9284
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707713210.1306
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707713747.5115
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "Pix2PixZero",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707715613.7226
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707765708.2644
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "CycleDiffusion",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707765861.2742
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "CycleDiffusion",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707765975.0206
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "CycleDiffusion",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707768866.9065
+  },
+  {
+    "model_a": "SDEdit",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707771673.2989
+  },
+  {
+    "model_a": "SDEdit",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707784377.6617
+  },
+  {
+    "model_a": "SDEdit",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707784466.8915
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "PNP",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707784983.9581
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707785277.16
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707795299.0619
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "SDEdit",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707795798.752
+  },
+  {
+    "model_a": "SDEdit",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707796435.7996
+  },
+  {
+    "model_a": "SDEdit",
+    "model_b": "CycleDiffusion",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707797278.7369
+  },
+  {
+    "model_a": "SDEdit",
+    "model_b": "CycleDiffusion",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707797279.6004
+  },
+  {
+    "model_a": "SDEdit",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707805086.9739
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707805220.3253
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "CycleDiffusion",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707805332.6322
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707805476.0509
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707818374.3438
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707834631.9088
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707834954.0147
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "Pix2PixZero",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707835366.544
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707835643.6178
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707835789.25
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "PNP",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707836852.671
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707836952.6082
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "SDEdit",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707837020.7148
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "PNP",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707837226.2259
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "Pix2PixZero",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707838166.1449
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "MagicBrush",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707838405.0013
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "CycleDiffusion",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707839133.3126
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707839484.6824
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "InstructPix2Pix",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707850104.2499
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "Pix2PixZero",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707851384.7689
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707851936.9466
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "MagicBrush",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707852836.3291
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "MagicBrush",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707852878.673
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707853008.1359
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "Pix2PixZero",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707856807.6229
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "Pix2PixZero",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707863740.3507
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "PNP",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707866312.1118
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707883083.3533
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707883181.1397
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707883187.9173
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "Prompt2prompt",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707883507.587
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "CycleDiffusion",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707883939.6125
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707892689.4407
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707908988.749
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707912639.2701
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "Pix2PixZero",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707917685.9574
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707919429.336
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "CycleDiffusion",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707932651.9192
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707932749.3107
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "PNP",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1707933208.5797
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "Pix2PixZero",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1707945335.6341
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "PNP",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708031168.6838
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "PNP",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708038931.5388
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "CycleDiffusion",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708057382.78
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708093689.8237
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "PNP",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708093910.4683
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708095090.8232
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "Prompt2prompt",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708095305.4665
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "Prompt2prompt",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708140553.1694
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "Prompt2prompt",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708145512.3656
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "Prompt2prompt",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708145724.4127
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "PNP",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708146846.5098
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "MagicBrush",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708189738.4864
+  },
+  {
+    "model_a": "Prompt2prompt",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708235874.9246
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "PNP",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708257619.7115
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "Pix2PixZero",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708341265.7655
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708350183.3086
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "Pix2PixZero",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708399707.1681
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "MagicBrush",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708441502.4707
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "MagicBrush",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708441716.8195
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708546759.2009
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "MagicBrush",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708546805.4892
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "CycleDiffusion",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708547082.7124
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708547166.9685
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708547293.7107
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "PNP",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708575046.0529
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "MagicBrush",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1708615466.9264
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1708615516.3341
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "PNP",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1709205399.0098
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "PNP",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1709205767.8923
+  },
+  {
+    "model_a": "PNP",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_b",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1709443700.05
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "Pix2PixZero",
+    "winner": "model_a",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1709702898.9291
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "Prompt2prompt",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1710091925.1861
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1710517781.1525
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": false,
+    "tstamp": 1710517859.2942
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "CycleDiffusion",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_::1",
+    "anony": true,
+    "tstamp": 1710535672.9791
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "Pix2PixZero",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711610477.1213
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "Pix2PixZero",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711629129.3894
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "CycleDiffusion",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711629705.2246
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "Pix2PixZero",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711630362.5575
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_127.0.0.1",
+    "anony": false,
+    "tstamp": 1711631112.5207
+  },
+  {
+    "model_a": "Pix2PixZero",
+    "model_b": "Prompt2prompt",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711631690.5127
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_a",
+    "judge": "arena_user_127.0.0.1",
+    "anony": false,
+    "tstamp": 1711633200.2923
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "InstructPix2Pix",
+    "winner": "model_a",
+    "judge": "arena_user_127.0.0.1",
+    "anony": false,
+    "tstamp": 1711633594.9922
+  },
+  {
+    "model_a": "MagicBrush",
+    "model_b": "SDEdit",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711635443.3071
+  },
+  {
+    "model_a": "CycleDiffusion",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.25.191",
+    "anony": false,
+    "tstamp": 1711635899.3088
+  },
+  {
+    "model_a": "SDEdit",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.41.118",
+    "anony": false,
+    "tstamp": 1711639015.428
+  },
+  {
+    "model_a": "InstructPix2Pix",
+    "model_b": "MagicBrush",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.7.189",
+    "anony": false,
+    "tstamp": 1711646372.1201
+  }
+]

arena_elo/results/latest/elo_results_image_editing.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cef00c45d392a30913b367825270fcee5fd29e5c830866eef3d07146b3502f3
-size 57091
+oid sha256:1430e6703dd6fc1e5b8ce06b11bb3a47516763a33edaf99e4c8547da5d9a8516
+size 57064

arena_elo/results/latest/elo_results_t2i_generation.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f525abe69feb822d341929b27ef7660ddd5e6ff0491bed8383a8e3d19f0342bd
-size 62414
+oid sha256:e963f9d4b66d29c2f05a3923eff56cebd1f09b07223ac069456e08dc6143cda8
+size 66894

arena_elo/results/latest/image_editing_leaderboard.csv

@@ -1,8 +1,8 @@
 key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
-Prompt2prompt,Prompt2prompt,1227.5508595026165,1182.7966878908553,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io
-InstructPix2Pix,InstructPix2Pix,1160.2057367236093,1104.6020920372373,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
-PNP,PNP,1142.693603173293,1163.4165011464634,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
-MagicBrush,MagicBrush,1053.1728944865915,1104.2259166081321,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush
-Pix2PixZero,Pix2PixZero,918.6047552604578,899.6573774461386,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io
-CycleDiffusion,CycleDiffusion,865.0529105743963,820.8487760803515,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion
-SDEdit,SDEdit,632.7192402790356,724.4526487908217,MIT License,Stanford University,https://sde-image-editing.github.io
+Prompt2prompt,Prompt2prompt,1227.5508595026165,1158.5510681980204,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io
+InstructPix2Pix,InstructPix2Pix,1160.2057367236093,1071.0628993075604,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
+PNP,PNP,1142.693603173293,1165.4957550490212,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
+MagicBrush,MagicBrush,1053.1728944865915,1130.5422054860635,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush
+Pix2PixZero,Pix2PixZero,918.6047552604578,960.3217617445996,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io
+CycleDiffusion,CycleDiffusion,865.0529105743963,813.4794423328381,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion
+SDEdit,SDEdit,632.7192402790356,700.546867881897,MIT License,Stanford University,https://sde-image-editing.github.io

arena_elo/results/latest/t2i_generation_leaderboard.csv

@@ -1,10 +1,10 @@
 key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
-Playground v2.5,Playground v2.5,1226.2872445351936,1246.1685934024742,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
-StableCascade,StableCascade,1105.3322734027522,1087.9198960927265,stable-cascade-nc-community (other),Stability AI,https://huggingface.co/stabilityai/stable-cascade
-Playground v2,Playground v2,1091.4371447234744,1090.676108819673,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
-SDXLLightning,SDXLLightning,1043.235902888147,1045.0529259890538,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
-PixArtAlpha,PixArtAlpha,1020.6412075829058,1006.9966036187151,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
-SDXL,SDXL,964.7626495363717,969.5241392802999,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
-SDXLTurbo,SDXLTurbo,912.2113859675355,914.3805456579931,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
-OpenJourney,OpenJourney,841.2224045541894,832.2282703082603,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
-LCM,LCM,794.8697868094328,810.2118373597045,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7
+Playground v2.5,Playground v2.5,1226.2872445351936,1236.5076527218755,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
+StableCascade,StableCascade,1105.3322734027522,1062.0980902577003,stable-cascade-nc-community (other),Stability AI,https://huggingface.co/stabilityai/stable-cascade
+Playground v2,Playground v2,1091.4371447234744,1087.3576445526567,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
+SDXLLightning,SDXLLightning,1043.235902888147,1019.4526672266176,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
+PixArtAlpha,PixArtAlpha,1020.6412075829058,1001.5090282446616,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
+SDXL,SDXL,964.7626495363717,969.8928133531979,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+SDXLTurbo,SDXLTurbo,912.2113859675355,914.9478831930971,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
+OpenJourney,OpenJourney,841.2224045541894,835.4563491411935,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
+LCM,LCM,794.8697868094328,812.962889153237,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7

arena_elo/update_elo_rating.sh

@@ -1,7 +1,7 @@
 # set LOGDIR to default if not set before
 if [ -z "$LOGDIR" ]; then
-    echo "LOGDIR is not set. Please set LOGDIR to the directory where the logs will be stored. Command: export LOGDIR=/path/to/logdir"
-    exit 1
+    echo "LOGDIR is not set. Using default '../GenAI-Arena-hf-logs/vote_log'"
+    export LOGDIR="../GenAI-Arena-hf-logs/vote_log"
 fi
 
 mkdir -p results
@@ -16,8 +16,8 @@ generation_battle_cutoff_date=`cat cut_off_date.txt` && rm cut_off_date.txt && e
 mkdir -p ./results/$edition_battle_cutoff_date
 mkdir -p ./results/$generation_battle_cutoff_date
 
-cp clean_battle_image_editing_$edition_battle_cutoff_date.json ./results/latest/
-cp clean_battle_t2i_generation_$generation_battle_cutoff_date.json ./results/latest/
+cp clean_battle_image_editing_$edition_battle_cutoff_date.json ./results/latest/clean_battle_image_editing.json
+cp clean_battle_t2i_generation_$generation_battle_cutoff_date.json ./results/latest/clean_battle_t2i_generation.json
 mv clean_battle_image_editing_$edition_battle_cutoff_date.json ./results/$edition_battle_cutoff_date/clean_battle_image_editing.json
 mv clean_battle_t2i_generation_$generation_battle_cutoff_date.json ./results/$generation_battle_cutoff_date/clean_battle_t2i_generation.json