Note This is a dataset to classify AI slop.

bench-labs/PixelModel-v5

Text-to-Image • 0.2B • Updated 5 days ago • 5.94k • 31

Note almost the same as v4 but has more training data

bench-labs/VoxelModel-v1

Text-to-3D • 40.2M • Updated 3 days ago • 1.14k • 14

Note VoxelModel v1: tiny text-to-3D voxel diffusion

bench-labs/PixelModel-v4

Text-to-Image • 40.1M • Updated 11 days ago • 4.49k • 9

Note a tiny latent diffusion transformer, and the result is a roughly 10x jump in FID.

bench-labs/PixelModel-v3

Text-to-Image • 919k • Updated 11 days ago • 4.5k • 8

Note New architecture, not a scale-up. SIREN decoder + FiLM + learned embeddings. Beats v1 FID.

bench-labs/PixelModel-v2

Text-to-Image • 200k • Updated 11 days ago • 4.36k • 10

Note scaled up

Note 300 dual-mode evaluation items, balanced across all 17 Bench Labs categories

Note 300 dual-mode evaluation items, balanced across all 17 Bench Labs categories

Note 300 dual-mode evaluation items, balanced across all 17 Bench Labs categories

Note The leaderboard is here, let's evaluate

bench-labs/pixelmodel-v1

Text-to-Image • 23.7k • Updated 11 days ago • 4.09k • 10

Note A continuation of previous pixelmodel

Note A mid quality benchmark.

Note Our new benchmark, comes with a custoom script.

Note 240 rows simple benchmark

bench-labs/pixelmodel

Text-to-Image • 203k • Updated 11 days ago • 4.31k • 6

Note A toy, fun to play with. text to image model

Note Our blog.