BenchLabs Models
Two tiny diffusion models, running live on CPU, no GPU behind this Space. Both are under 45M trained parameters, so generation is slower than a hosted API but the whole model fits in a PNG image if you're curious — see the model pages linked below.
A larger MMDiT model conditioned by T5 and CLIP. CPU generation is slower; 256x256 output.
10 100
1 10
Examples
| Prompt | Detail (sampling steps) | Prompt strength (CFG) | Seed |
|---|
Good at bulky objects: chairs, tables, cars, mushrooms. Thin objects (swords, keys) don't survive 32³ voxelization, in the training data or the model, so expect a blob rather than a blade.
10 50
1 10
-1 1
Examples
| Prompt | Detail (sampling steps) | Prompt strength (CFG) | Occupancy threshold | Seed |
|---|
Good at material and light: food, landscapes, skies, interiors. Weak on faces, hands, and anything needing precise structure or text.
10 50
1 10
Examples
| Prompt | Detail (sampling steps) | Prompt strength (CFG) | Seed |
|---|
Models: PixelModel v5 · VoxelModel v1