AI open-source project
speridlabs/iris-3b
Iris-3B: pixel-space generation & general vision learner. A 3B diffusion transformer that generates every pixel directly (no VAE); the same prior, fine-tuned, does monocular depth estimation and 4x image restoration. Paper, weights, training code and demo.
- Stars
- 218
- 7d
- Collecting data
- 30d
- Collecting data
Star history (UTC)
- 218
Metrics without today’s or the matching baseline snapshot remain unavailable.