Repository · GitHub
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.
| Owner | speridlabs |
|---|---|
| License (as declared) | Apache-2.0 |
| Stars | 185 |
| Forks | 17 |
| Main language | Python |
| Created | 5 October 2026 |
| Last updated at source | 15 October 2026 |
Stars, last 3 days
185 now (+2 since 2026-10-16). Counts as reported by the source, snapshotted daily by Silytics.
Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.