bench-labs/PixelModel-v5

Text-to-Image • 0.2B • Updated about 4 hours ago • 2

Note almost the same as v4 but has more training data

bench-labs/PixelModel-v4

Text-to-Image • 40.1M • Updated 3 days ago • 23 • 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 3 days ago • 91 • 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 3 days ago • 56 • 10

Note scaled up

bench-labs/pixelmodel-v1

Text-to-Image • 23.7k • Updated 7 days ago • 106 • 10

Note x8.5 smaller, more efficient, better prompt understanding and larger training dataset

bench-labs/pixelmodel

Text-to-Image • 203k • Updated 11 days ago • 66 • 6

Note The first of its kind.