Spaces:
Running
Running
Refactor app.py to implement a new leaderboard for inference providers, focusing on cost, quality, and speed. Added data processing from a new CSV file and updated the Gradio interface. Removed unused modules and files to streamline the codebase.
099bd02
| Provider,URL,GenEval,HPS (v2.1),GenAI-Bench (VQA),DrawBench (Image Reward),PartiPromts (ARNIQA),PartiPromts (ClipIQA),PartiPromts (ClipScore),PartiPromts (CMMD to Baseline),PartiPromts (Sharpness - Laplacian Variance),Median Inference Time (in s),Price per Image | |
| Baseline [Nvidia H100],https://huggingface.co/black-forest-labs/FLUX.1-dev?library=diffusers,67.98,30.36,0.74,1.0072,0.6758,0.8968,27.4,0,6833,6.88,0.025 | |
| fal,https://fal.ai/models/fal-ai/flux/dev,68.72,29.97,0.7441,1.0084,0.6702,0.8967,27.61,0.008,7295,4.06,0.025 | |
| Fireworks [fp8],https://fireworks.ai/models/fireworks/flux-1-dev-fp8,65.55,30.26,0.7455,0.9467,0.6639,0.8478,27.24,0.021,5625,4.66,0.014 | |
| Pruna [extra juiced],https://replicate.com/prunaai/flux.1-juiced,69.9,29.86,0.7466,0.9458,0.6591,0.8887,27.6,0.029,7997,2.6,40 | |
| Pruna [juiced],https://replicate.com/prunaai/flux.1-juiced,68.64,30.38,0.7408,0.9657,0.6762,0.9014,27.55,0.014,7627,3.14,48 | |
| Pruna [lightly juiced],https://replicate.com/prunaai/flux.1-juiced,69.12,30.36,0.7405,0.9972,0.6789,0.9031,27.56,0.012,7849,3.57,54 | |
| Replicate [go_fast],https://replicate.com/black-forest-labs/flux-dev,67.41,29.25,0.7547,0.9282,0.6356,0.8609,27.56,0.019,4872,3.38,0.025 | |
| Together AI,https://www.together.ai/models/flux-1-dev,64.61,30.22,0.7339,0.9463,0.5752,0.8709,27.31,0.2,4501,3.38,0.025 | |