bench-labs/VoxelModel-v1

Text-to-3D • 40.2M • Updated about 3 hours ago • 4

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

Note These little grazing cows used to live on the bench-labs blog. Now they have their own hill — click a cow to pat it!

bench-labs/PixelModel-v4

Text-to-Image • 40.1M • Updated 1 day ago • 16 • 5

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 1 day ago • 90 • 7

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

bench-labs/PixelModel-v2

Text-to-Image • 200k • Updated 1 day ago • 54 • 9

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

Note This artifact is part of a larger research, we do not recommmend the usage of this data corpus.

bench-labs/pixelmodel-v1

Text-to-Image • 23.7k • Updated 5 days ago • 106 • 10

Note A continuation of previous pixelmodel

Note recursive self improvement for AGI, still updating

Note A mid quality benchmark.

Note Our new benchmark, comes with a custoom script.

Note We seek colaborators to utilize our benchmarks and work with us

Note 240 rows simple benchmark

bench-labs/pixelmodel

Text-to-Image • 203k • Updated 9 days ago • 66 • 6

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

Note Our blog.