Auto Daily Leaderboard udpate Fri Dec 6 12:00:28 PM EST 2024

arena_elo/results/20241205/elo_results_image_editing.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c76d28d54f27d049d329e4244b9902b881caf1935871ed3d5dabedb19ac4056
+size 63250

arena_elo/results/20241205/image_editing_leaderboard.csv

@@ -0,0 +1,10 @@
+key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
+MagicBrush,MagicBrush,1107.2711524404608,1111.352765273051,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush/
+InfEdit,InfEdit,1074.691952122568,1074.3888664969325,CC BY-NC-ND 4.0,"University of Michigan, University of California, Berkeley",https://sled-group.github.io/InfEdit/
+CosXLEdit,CosXLEdit,1068.2892784182402,1069.1933224307186,cosxl-nc-community,Stability AI,https://huggingface.co/stabilityai/cosxl
+InstructPix2Pix,InstructPix2Pix,1039.531239136446,1037.2511749191217,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
+PNP,PNP,997.0819250402586,1001.6454737363559,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
+Prompt2prompt,Prompt2prompt,988.1595273894258,989.2720618087155,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io/
+CycleDiffusion,CycleDiffusion,942.4786479539531,936.182429018157,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion?tab=readme-ov-file
+SDEdit,SDEdit,925.6636017423486,924.0947113264285,MIT License,Stanford University,https://sde-image-editing.github.io
+Pix2PixZero,Pix2PixZero,856.8326757562992,856.6191949905194,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io/

arena_elo/results/20241206/elo_results_t2i_generation.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e2fe377a0198f8644ed658f0983e3031c93be4afbce5996cea3500481c2622
+size 88250

arena_elo/results/20241206/t2i_generation_leaderboard.csv

@@ -0,0 +1,18 @@
+key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
+FLUX.1-dev,FLUX.1-dev,1122.923510940922,1140.5941949143137,flux-1-dev-non-commercial-license (other),Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2.5,PlayGround V2.5,1118.5693726039096,1118.8022943397657,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
+FLUX.1-schnell,FLUX.1-schnell,1088.7995468237616,1079.6429218477758,Apache-2.0,Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2,PlayGround V2,1073.1356784208829,1071.7177932289221,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
+Kolors,Kolors,1052.5891726181997,1051.1627612096615,Apache-2.0,Kwai Kolors,https://huggingface.co/Kwai-Kolors/Kolors
+StableCascade,StableCascade,1040.0630780085105,1042.225708679194,stable-cascade-nc-community (other),Stability AI,https://fal.ai/models/stable-cascade/api
+HunyuanDiT,HunyuanDiT,1022.7272370130091,1016.21919883135,tencent-hunyuan-community,Tencent,https://github.com/Tencent/HunyuanDiT
+PixArtAlpha,PixArtAlpha,1019.1982787357837,1010.5402080967344,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
+SDXL-Lightning,SDXL-Lightning,1018.6201982931565,1021.797781246543,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
+PixArtSigma,PixArtSigma,1018.2359921724576,1017.7736346262005,openrail++,PixArt-alpha,https://github.com/PixArt-alpha/PixArt-sigma
+SD3,SD3,1008.8736798911177,1011.5505310622475,stabilityai-nc-research-community,Stability AI,https://huggingface.co/blog/sd3
+AuraFlow,AuraFlow,1001.9306379660595,996.2845832371092,Apache-2.0,Fal.AI,https://huggingface.co/fal/AuraFlow
+SDXL,SDXL,967.5730123892811,967.5295760624575,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+SDXLTurbo,SDXLTurbo,916.0850881685112,913.3917799636163,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
+LCM(v1.5/XL),LCM(v1.5/XL),905.8243590905762,899.2812138143674,openrail++,Latent Consistency,https://fal.ai/models/fast-lcm-diffusion-turbo
+OpenJourney,OpenJourney,833.5019499271361,827.679359941643,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
+LCM,LCM,791.3492069367272,804.9851217565837,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7

arena_elo/results/latest/clean_battle_image_editing.json

@@ -19688,5 +19688,21 @@
     "judge": "arena_user_10.20.38.251",
     "anony": true,
     "tstamp": 1732630423.8649
+  },
+  {
+    "model_a_conv_id": "4032f7961f9340bfa117c1a466dcd56f",
+    "model_b_conv_id": "f097721eeabd47d5bc49192141a90c4c",
+    "inputs": {
+      "source_prompt": "A zebra with a single front leg grazing on lush green grass in a field.",
+      "target_prompt": "A zebra with a single front leg grazing on lush green grass in a field, showing its teeth.",
+      "instruct_prompt": "Open the zebra's mouth."
+    },
+    "model_a": "Prompt2prompt",
+    "model_b": "CosXLEdit",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.38.196",
+    "anony": true,
+    "tstamp": 1733435624.5129
   }
 ]

arena_elo/results/latest/clean_battle_t2i_generation.json

@@ -109502,5 +109502,131 @@
     "judge": "arena_user_10.16.30.109",
     "anony": true,
     "tstamp": 1733416881.6244
+  },
+  {
+    "model_a_conv_id": "425d64bff94846ebab92dff8636de842",
+    "model_b_conv_id": "69cb8b62582a47ae8d01ebb931ea4a9c",
+    "inputs": {
+      "prompt": "a black and white cat sitting on a brown suitcase next to a wall"
+    },
+    "model_a": "OpenJourney",
+    "model_b": "FLUX.1-dev",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.20.26.107",
+    "anony": true,
+    "tstamp": 1733437935.1337
+  },
+  {
+    "model_a_conv_id": "0b2bdec853074dd8b7961d6a9aff03be",
+    "model_b_conv_id": "10c46f1b25b24dc4a6cf51490b9ad7fd",
+    "inputs": {
+      "prompt": "image of massive statue of Donald Trump in columbus mall, highly detailed"
+    },
+    "model_a": "SDXL",
+    "model_b": "FLUX.1-dev",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.20.26.107",
+    "anony": true,
+    "tstamp": 1733437942.7064
+  },
+  {
+    "model_a_conv_id": "60ddb5dbd6f744d893a2d77204edbf18",
+    "model_b_conv_id": "2f42d3b79f25439bb40d35fdef06b99a",
+    "inputs": {
+      "prompt": "stylish cyberpunk girl with tattoo and wild colorful hair, detailed cafe background full body, fine detail, anime, realistic shaded lighting, directional lighting 2 d poster by ilya kuvshinov, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey "
+    },
+    "model_a": "StableCascade",
+    "model_b": "FLUX.1-schnell",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.20.38.195",
+    "anony": true,
+    "tstamp": 1733437952.9419
+  },
+  {
+    "model_a_conv_id": "40e0be2540cd41d68cd2360032f53358",
+    "model_b_conv_id": "009dd268aece47a78fbe30af09618eb8",
+    "inputs": {
+      "prompt": "A small blue book sitting on a large red book."
+    },
+    "model_a": "SDXL",
+    "model_b": "StableCascade",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.20.38.195",
+    "anony": true,
+    "tstamp": 1733437965.4122
+  },
+  {
+    "model_a_conv_id": "18123c15647648c097cfdb55a72e99bb",
+    "model_b_conv_id": "3d3b8be4fc07451495bd22507d1ff526",
+    "inputs": {
+      "prompt": "An ancient Egyptian painting depicting an argument over whose turn it is to take out the trash."
+    },
+    "model_a": "PixArtAlpha",
+    "model_b": "Kolors",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.38.136",
+    "anony": true,
+    "tstamp": 1733465735.2921
+  },
+  {
+    "model_a_conv_id": "3a8467f2c2af4d3e8c2a012ff5d582f2",
+    "model_b_conv_id": "fc63bb6aaa28476bb0b7ef707b55e486",
+    "inputs": {
+      "prompt": "Jentacular."
+    },
+    "model_a": "SDXL",
+    "model_b": "StableCascade",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.20.38.195",
+    "anony": true,
+    "tstamp": 1733475299.4001
+  },
+  {
+    "model_a_conv_id": "cde95cda80704ffcb5336d0412999ebf",
+    "model_b_conv_id": "59a38650987d40d99e1c3430d6dd94dc",
+    "inputs": {
+      "prompt": "Девушка мастурбирует"
+    },
+    "model_a": "AuraFlow",
+    "model_b": "FLUX.1-schnell",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.20.26.107",
+    "anony": true,
+    "tstamp": 1733475316.8859
+  },
+  {
+    "model_a_conv_id": "5e19fd047749476daa78c3436c56fab9",
+    "model_b_conv_id": "f9ec7fee2d634c01893437eb10a19af1",
+    "inputs": {
+      "prompt": "A tennis racket underneath a traffic light."
+    },
+    "model_a": "StableCascade",
+    "model_b": "OpenJourney",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.20.38.195",
+    "anony": true,
+    "tstamp": 1733480606.3479
+  },
+  {
+    "model_a_conv_id": "43a77ba5791347408e8ee794b9b0791d",
+    "model_b_conv_id": "c61b37e2e6304f8b804199eb5a36a6d7",
+    "inputs": {
+      "prompt": "Four cars on the street."
+    },
+    "model_a": "FLUX.1-dev",
+    "model_b": "StableCascade",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.20.38.195",
+    "anony": true,
+    "tstamp": 1733480620.7524
   }
 ]

arena_elo/results/latest/elo_results_image_editing.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf7a18b49d21184c92659b1885a93ed4dd595a642736c7c8845d368b629d195
+oid sha256:1c76d28d54f27d049d329e4244b9902b881caf1935871ed3d5dabedb19ac4056
 size 63250

arena_elo/results/latest/elo_results_t2i_generation.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944e0986e964e4766a96d45c78660f1b12d2fc7023a957e601af6fa6f737ef23
+oid sha256:b4e2fe377a0198f8644ed658f0983e3031c93be4afbce5996cea3500481c2622
 size 88250

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,1107.2523468920663,1111.3359673778732,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush/
-InfEdit,InfEdit,1074.6681383592995,1074.366568165408,CC BY-NC-ND 4.0,"University of Michigan, University of California, Berkeley",https://sled-group.github.io/InfEdit/
-CosXLEdit,CosXLEdit,1067.1852498305389,1068.1159156502054,cosxl-nc-community,Stability AI,https://huggingface.co/stabilityai/cosxl
-InstructPix2Pix,InstructPix2Pix,1039.5821277313255,1037.2991472309634,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
-PNP,PNP,997.1116941557656,1001.6744424533496,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
-Prompt2prompt,Prompt2prompt,989.1401514709111,990.234961285272,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io/
-CycleDiffusion,CycleDiffusion,942.485204026653,936.1704318305718,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion?tab=readme-ov-file
-SDEdit,SDEdit,925.6912657460032,924.1254182192059,MIT License,Stanford University,https://sde-image-editing.github.io
-Pix2PixZero,Pix2PixZero,856.883821787437,856.6771477871511,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io/
+MagicBrush,MagicBrush,1107.2711524404608,1111.352765273051,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush/
+InfEdit,InfEdit,1074.691952122568,1074.3888664969325,CC BY-NC-ND 4.0,"University of Michigan, University of California, Berkeley",https://sled-group.github.io/InfEdit/
+CosXLEdit,CosXLEdit,1068.2892784182402,1069.1933224307186,cosxl-nc-community,Stability AI,https://huggingface.co/stabilityai/cosxl
+InstructPix2Pix,InstructPix2Pix,1039.531239136446,1037.2511749191217,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
+PNP,PNP,997.0819250402586,1001.6454737363559,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
+Prompt2prompt,Prompt2prompt,988.1595273894258,989.2720618087155,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io/
+CycleDiffusion,CycleDiffusion,942.4786479539531,936.182429018157,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion?tab=readme-ov-file
+SDEdit,SDEdit,925.6636017423486,924.0947113264285,MIT License,Stanford University,https://sde-image-editing.github.io
+Pix2PixZero,Pix2PixZero,856.8326757562992,856.6191949905194,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
-FLUX.1-dev,FLUX.1-dev,1123.7080035827469,1141.2891841418273,flux-1-dev-non-commercial-license (other),Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
-PlayGround V2.5,PlayGround V2.5,1118.3391473064883,1118.641929211121,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
-FLUX.1-schnell,FLUX.1-schnell,1089.551494793911,1080.239294803794,Apache-2.0,Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
-PlayGround V2,PlayGround V2,1072.6697265052724,1071.262455720204,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
-Kolors,Kolors,1054.530238112381,1053.1143704693143,Apache-2.0,Kwai Kolors,https://huggingface.co/Kwai-Kolors/Kolors
-StableCascade,StableCascade,1039.955508936773,1042.0999164206312,stable-cascade-nc-community (other),Stability AI,https://fal.ai/models/stable-cascade/api
-HunyuanDiT,HunyuanDiT,1022.6531687144616,1016.1449539091337,tencent-hunyuan-community,Tencent,https://github.com/Tencent/HunyuanDiT
-PixArtAlpha,PixArtAlpha,1018.5737893680387,1009.9436406069414,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
-SDXL-Lightning,SDXL-Lightning,1018.3267146260313,1021.5340851971843,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
-PixArtSigma,PixArtSigma,1017.9418338006467,1017.4951756669981,openrail++,PixArt-alpha,https://github.com/PixArt-alpha/PixArt-sigma
-SD3,SD3,1008.837811777844,1011.4876289571108,stabilityai-nc-research-community,Stability AI,https://huggingface.co/blog/sd3
-AuraFlow,AuraFlow,1003.2010337702219,997.561039508895,Apache-2.0,Fal.AI,https://huggingface.co/fal/AuraFlow
-SDXL,SDXL,966.7848243484208,966.8087655550715,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
-SDXLTurbo,SDXLTurbo,915.6849148784231,912.988811912816,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
-LCM(v1.5/XL),LCM(v1.5/XL),905.4019046047279,898.885053786297,openrail++,Latent Consistency,https://fal.ai/models/fast-lcm-diffusion-turbo
-OpenJourney,OpenJourney,833.0224018571655,827.1975087124213,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
-LCM,LCM,790.8174830164403,804.4741171861567,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7
+FLUX.1-dev,FLUX.1-dev,1122.923510940922,1140.5941949143137,flux-1-dev-non-commercial-license (other),Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2.5,PlayGround V2.5,1118.5693726039096,1118.8022943397657,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
+FLUX.1-schnell,FLUX.1-schnell,1088.7995468237616,1079.6429218477758,Apache-2.0,Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2,PlayGround V2,1073.1356784208829,1071.7177932289221,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
+Kolors,Kolors,1052.5891726181997,1051.1627612096615,Apache-2.0,Kwai Kolors,https://huggingface.co/Kwai-Kolors/Kolors
+StableCascade,StableCascade,1040.0630780085105,1042.225708679194,stable-cascade-nc-community (other),Stability AI,https://fal.ai/models/stable-cascade/api
+HunyuanDiT,HunyuanDiT,1022.7272370130091,1016.21919883135,tencent-hunyuan-community,Tencent,https://github.com/Tencent/HunyuanDiT
+PixArtAlpha,PixArtAlpha,1019.1982787357837,1010.5402080967344,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
+SDXL-Lightning,SDXL-Lightning,1018.6201982931565,1021.797781246543,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
+PixArtSigma,PixArtSigma,1018.2359921724576,1017.7736346262005,openrail++,PixArt-alpha,https://github.com/PixArt-alpha/PixArt-sigma
+SD3,SD3,1008.8736798911177,1011.5505310622475,stabilityai-nc-research-community,Stability AI,https://huggingface.co/blog/sd3
+AuraFlow,AuraFlow,1001.9306379660595,996.2845832371092,Apache-2.0,Fal.AI,https://huggingface.co/fal/AuraFlow
+SDXL,SDXL,967.5730123892811,967.5295760624575,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+SDXLTurbo,SDXLTurbo,916.0850881685112,913.3917799636163,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
+LCM(v1.5/XL),LCM(v1.5/XL),905.8243590905762,899.2812138143674,openrail++,Latent Consistency,https://fal.ai/models/fast-lcm-diffusion-turbo
+OpenJourney,OpenJourney,833.5019499271361,827.679359941643,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
+LCM,LCM,791.3492069367272,804.9851217565837,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7