Auto Daily Leaderboard udpate Mon Sep 30 12:00:26 PM EDT 2024

arena_elo/results/20240929/elo_results_image_editing.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd45dfbf0a9a5ebe7b3f0613aa314f45aa2daf01225a93899477e0beadc2b55
+size 63245

arena_elo/results/20240929/image_editing_leaderboard.csv

@@ -0,0 +1,10 @@
+key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
+MagicBrush,MagicBrush,1109.135451232175,1113.1858367934767,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush/
+InfEdit,InfEdit,1075.1119298199667,1074.8971183930346,CC BY-NC-ND 4.0,"University of Michigan, University of California, Berkeley",https://sled-group.github.io/InfEdit/
+CosXLEdit,CosXLEdit,1064.8008852739117,1065.783984482586,cosxl-nc-community,Stability AI,https://huggingface.co/stabilityai/cosxl
+InstructPix2Pix,InstructPix2Pix,1038.5676440063037,1036.3208933569776,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
+PNP,PNP,998.5100321932698,1003.0847129645449,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
+Prompt2prompt,Prompt2prompt,988.1206223784635,989.2479173019008,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io/
+CycleDiffusion,CycleDiffusion,943.4514760291793,936.5195351501385,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion?tab=readme-ov-file
+SDEdit,SDEdit,923.9284621204279,922.3801801727517,MIT License,Stanford University,https://sde-image-editing.github.io
+Pix2PixZero,Pix2PixZero,858.3734969463025,858.579821384589,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io/

arena_elo/results/20240930/elo_results_t2i_generation.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e6e439a371b0697004f7f83bfdc4325b414bc876bcad254aedf1c4bcfc07f2
+size 88244

arena_elo/results/20240930/t2i_generation_leaderboard.csv

@@ -0,0 +1,18 @@
+key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
+PlayGround V2.5,PlayGround V2.5,1122.5270639450953,1125.0127561320196,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
+FLUX.1-dev,FLUX.1-dev,1110.5254236291642,1122.668367660175,flux-1-dev-non-commercial-license (other),Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+FLUX.1-schnell,FLUX.1-schnell,1091.6633585353488,1081.714184401561,Apache-2.0,Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2,PlayGround V2,1072.2691011245327,1071.512781569233,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
+Kolors,Kolors,1064.0963015070201,1059.6278841275089,Apache-2.0,Kwai Kolors,https://huggingface.co/Kwai-Kolors/Kolors
+StableCascade,StableCascade,1039.5581703598052,1042.4912848569556,stable-cascade-nc-community (other),Stability AI,https://fal.ai/models/stable-cascade/api
+HunyuanDiT,HunyuanDiT,1029.8030522489662,1022.1945198671765,tencent-hunyuan-community,Tencent,https://github.com/Tencent/HunyuanDiT
+SDXL-Lightning,SDXL-Lightning,1021.3173992704275,1024.8042875648832,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
+PixArtAlpha,PixArtAlpha,1021.1382631492593,1012.2454428605124,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
+PixArtSigma,PixArtSigma,1019.166673076227,1019.1913877606677,openrail++,PixArt-alpha,https://github.com/PixArt-alpha/PixArt-sigma
+SD3,SD3,1005.3854641817325,1010.3917189830572,stabilityai-nc-research-community,Stability AI,https://huggingface.co/blog/sd3
+AuraFlow,AuraFlow,1001.8939949067359,994.7255025170468,Apache-2.0,Fal.AI,https://huggingface.co/fal/AuraFlow
+SDXL,SDXL,964.9221337708851,965.8224712860441,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+SDXLTurbo,SDXLTurbo,913.7475571381475,911.2840371083312,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
+LCM(v1.5/XL),LCM(v1.5/XL),904.9847702054977,899.4723658644424,openrail++,Latent Consistency,https://fal.ai/models/fast-lcm-diffusion-turbo
+OpenJourney,OpenJourney,827.7394173396949,823.0163320004636,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
+LCM,LCM,789.2618556114662,803.6009826459906,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7

arena_elo/results/latest/clean_battle_image_editing.json

@@ -19400,5 +19400,21 @@
     "judge": "arena_user_10.16.10.147",
     "anony": true,
     "tstamp": 1727370797.8595
+  },
+  {
+    "model_a_conv_id": "94e4c116bb8b42e7823c3ae55c814bce",
+    "model_b_conv_id": "56c2bd509a9a425f82873496d591b80b",
+    "inputs": {
+      "source_prompt": "An intersection with street signs and traffic lights and someone riding on a bicycle with a plane in the sky.",
+      "target_prompt": "An intersection with street signs and traffic lights and someone riding on a bicycle with a clear blue sky and a plane in the distance.",
+      "instruct_prompt": "remove the clouds"
+    },
+    "model_a": "CycleDiffusion",
+    "model_b": "Prompt2prompt",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.32.208",
+    "anony": true,
+    "tstamp": 1727650046.4763
   }
 ]

arena_elo/results/latest/clean_battle_t2i_generation.json

@@ -102838,5 +102838,33 @@
     "judge": "arena_user_10.16.46.55",
     "anony": true,
     "tstamp": 1727613802.1802
+  },
+  {
+    "model_a_conv_id": "ee037a33548a42e58f36d1b789b88213",
+    "model_b_conv_id": "afbcf20b347d45c793d7e6abaa702dd7",
+    "inputs": {
+      "prompt": "boob"
+    },
+    "model_a": "PlayGround V2.5",
+    "model_b": "SDXL",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.18.75",
+    "anony": true,
+    "tstamp": 1727643274.8337
+  },
+  {
+    "model_a_conv_id": "73ee246365e84a91b8c66e5040a40c77",
+    "model_b_conv_id": "89ca3098a1ba491fb6091802762562c8",
+    "inputs": {
+      "prompt": "photorealistic, detailed mechanical motorcycle, detailed"
+    },
+    "model_a": "OpenJourney",
+    "model_b": "SDXL",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.18.75",
+    "anony": true,
+    "tstamp": 1727679893.568
   }
 ]

arena_elo/results/latest/elo_results_image_editing.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:550a3bf74b5fb57c83d7f34e961e152cf1c13c78234c1f562225a6275cae75f8
+oid sha256:bcd45dfbf0a9a5ebe7b3f0613aa314f45aa2daf01225a93899477e0beadc2b55
 size 63245

arena_elo/results/latest/elo_results_t2i_generation.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180e6d83897e8bbfc9104c81a8e94f82dccabc1814e37ef1af846a3d12c3f9f3
+oid sha256:09e6e439a371b0697004f7f83bfdc4325b414bc876bcad254aedf1c4bcfc07f2
 size 88244

arena_elo/results/latest/image_editing_leaderboard.csv

@@ -1,10 +1,10 @@
 key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
-MagicBrush,MagicBrush,1109.1416770434666,1113.185401787606,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush/
-InfEdit,InfEdit,1075.187201868628,1074.9688036745556,CC BY-NC-ND 4.0,"University of Michigan, University of California, Berkeley",https://sled-group.github.io/InfEdit/
-CosXLEdit,CosXLEdit,1064.7548316773853,1065.7158269155223,cosxl-nc-community,Stability AI,https://huggingface.co/stabilityai/cosxl
-InstructPix2Pix,InstructPix2Pix,1038.577820029504,1036.3235273022021,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
-PNP,PNP,998.5397880385796,1003.1105954594531,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
-Prompt2prompt,Prompt2prompt,989.5140463177335,990.6505456460847,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io/
-CycleDiffusion,CycleDiffusion,941.905087437052,935.0138179148606,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion?tab=readme-ov-file
-SDEdit,SDEdit,923.985553246089,922.4232018760358,MIT License,Stanford University,https://sde-image-editing.github.io
-Pix2PixZero,Pix2PixZero,858.3939943415622,858.6082794236797,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io/
+MagicBrush,MagicBrush,1109.135451232175,1113.1858367934767,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush/
+InfEdit,InfEdit,1075.1119298199667,1074.8971183930346,CC BY-NC-ND 4.0,"University of Michigan, University of California, Berkeley",https://sled-group.github.io/InfEdit/
+CosXLEdit,CosXLEdit,1064.8008852739117,1065.783984482586,cosxl-nc-community,Stability AI,https://huggingface.co/stabilityai/cosxl
+InstructPix2Pix,InstructPix2Pix,1038.5676440063037,1036.3208933569776,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
+PNP,PNP,998.5100321932698,1003.0847129645449,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
+Prompt2prompt,Prompt2prompt,988.1206223784635,989.2479173019008,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io/
+CycleDiffusion,CycleDiffusion,943.4514760291793,936.5195351501385,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion?tab=readme-ov-file
+SDEdit,SDEdit,923.9284621204279,922.3801801727517,MIT License,Stanford University,https://sde-image-editing.github.io
+Pix2PixZero,Pix2PixZero,858.3734969463025,858.579821384589,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io/

arena_elo/results/latest/t2i_generation_leaderboard.csv

@@ -1,18 +1,18 @@
 key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
-PlayGround V2.5,PlayGround V2.5,1123.10583479656,1125.5124149086703,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
-FLUX.1-dev,FLUX.1-dev,1110.596049434876,1122.8669339745218,flux-1-dev-non-commercial-license (other),Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
-FLUX.1-schnell,FLUX.1-schnell,1091.6712399084631,1081.7255506562674,Apache-2.0,Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
-PlayGround V2,PlayGround V2,1072.2280855088052,1071.4515409928772,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
-Kolors,Kolors,1064.0915824284707,1059.625374729521,Apache-2.0,Kwai Kolors,https://huggingface.co/Kwai-Kolors/Kolors
-StableCascade,StableCascade,1039.5463791955835,1042.4661754242106,stable-cascade-nc-community (other),Stability AI,https://fal.ai/models/stable-cascade/api
-HunyuanDiT,HunyuanDiT,1029.8408157381361,1022.2228553468657,tencent-hunyuan-community,Tencent,https://github.com/Tencent/HunyuanDiT
-SDXL-Lightning,SDXL-Lightning,1021.3064019938304,1024.7845601062627,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
-PixArtAlpha,PixArtAlpha,1021.0862400923867,1012.1826571126029,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
-PixArtSigma,PixArtSigma,1019.1552271634681,1019.1717271966269,openrail++,PixArt-alpha,https://github.com/PixArt-alpha/PixArt-sigma
-SD3,SD3,1005.4019178081703,1010.4114446560138,stabilityai-nc-research-community,Stability AI,https://huggingface.co/blog/sd3
-AuraFlow,AuraFlow,1001.9191090405225,994.7477232337651,Apache-2.0,Fal.AI,https://huggingface.co/fal/AuraFlow
-SDXL,SDXL,964.4012530993016,965.3818433554069,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
-SDXLTurbo,SDXLTurbo,913.6892004297566,911.2122481181198,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
-LCM(v1.5/XL),LCM(v1.5/XL),904.9493296964522,899.4268843821743,openrail++,Latent Consistency,https://fal.ai/models/fast-lcm-diffusion-turbo
-OpenJourney,OpenJourney,827.8409729737498,823.0782209027642,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
-LCM,LCM,789.170360691459,803.5065163895399,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7
+PlayGround V2.5,PlayGround V2.5,1122.5270639450953,1125.0127561320196,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
+FLUX.1-dev,FLUX.1-dev,1110.5254236291642,1122.668367660175,flux-1-dev-non-commercial-license (other),Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+FLUX.1-schnell,FLUX.1-schnell,1091.6633585353488,1081.714184401561,Apache-2.0,Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2,PlayGround V2,1072.2691011245327,1071.512781569233,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
+Kolors,Kolors,1064.0963015070201,1059.6278841275089,Apache-2.0,Kwai Kolors,https://huggingface.co/Kwai-Kolors/Kolors
+StableCascade,StableCascade,1039.5581703598052,1042.4912848569556,stable-cascade-nc-community (other),Stability AI,https://fal.ai/models/stable-cascade/api
+HunyuanDiT,HunyuanDiT,1029.8030522489662,1022.1945198671765,tencent-hunyuan-community,Tencent,https://github.com/Tencent/HunyuanDiT
+SDXL-Lightning,SDXL-Lightning,1021.3173992704275,1024.8042875648832,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
+PixArtAlpha,PixArtAlpha,1021.1382631492593,1012.2454428605124,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
+PixArtSigma,PixArtSigma,1019.166673076227,1019.1913877606677,openrail++,PixArt-alpha,https://github.com/PixArt-alpha/PixArt-sigma
+SD3,SD3,1005.3854641817325,1010.3917189830572,stabilityai-nc-research-community,Stability AI,https://huggingface.co/blog/sd3
+AuraFlow,AuraFlow,1001.8939949067359,994.7255025170468,Apache-2.0,Fal.AI,https://huggingface.co/fal/AuraFlow
+SDXL,SDXL,964.9221337708851,965.8224712860441,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+SDXLTurbo,SDXLTurbo,913.7475571381475,911.2840371083312,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
+LCM(v1.5/XL),LCM(v1.5/XL),904.9847702054977,899.4723658644424,openrail++,Latent Consistency,https://fal.ai/models/fast-lcm-diffusion-turbo
+OpenJourney,OpenJourney,827.7394173396949,823.0163320004636,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
+LCM,LCM,789.2618556114662,803.6009826459906,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7