Speridlabs 发布像素空间生成模型 Iris-3B

Pixel-space generation & general vision learner

Iris-3B is a pixel-space generative model that can act as a general vision learner. Working in pixel space, it bypasses the lossy compression and the biased, texture-focused latents of a VAE. We show image generators can replace vision models such as DINOv2, release our pixel-space scaling recipes, and put the generative prior to work on dense tasks where detail matters.

Hanqiu Li Cai^†Chema GarabitoSperidlabs · † project lead

02 — Gallery

Gallery

03 — Architecture

Architecture

A 3B flow-matching transformer that generates raw RGB pixels directly, with no VAE in the loop.

FIG. 02 — ArchitectureTrunk · PiT head · trunk block

Images are cut into 16 × 16 pixel patches. The trunk has 8 dual-stream blocks, with separate text and image weights, followed by 16 single-stream blocks.

A small pixel-transformer (PiT) head decodes each patch token back to pixels. Text comes from a frozen Qwen3-VL-4B encoder, and 2D RoPE lets one set of weights run at any resolution and aspect ratio up to one megapixel.

04 — Benchmarks

Benchmarks

Competitive with state-of-the-art latent models on every official benchmark, at a fraction of their training compute.

Iris-3B: official evaluators at 1024², no prompt rewriting, no best-of-N. References from the Qwen-Image and Z-Image reports; — not reported; * uses prompt rewriting.

05 — Downstream

Downstream

Iris-3B tuned for downstream tasks.

05.A

Depth

Point clouds from predicted depth · drag to orbit, scroll to zoom

05.B

Image Restoration / Super-resolution

06 — Citation

Cite this work

@article{licai2026iris,
  title   = {Iris-3B: Going Beyond the Latent with Pixel-Space
             Diffusion Training, Conversion and Fine-Tuning},
  author  = {Li Cai, Hanqiu and Garabito, Chema},
  journal = {arXiv preprint arXiv:2610.09450},
  year    = {2026},
  url     = {https://arxiv.org/abs/2610.09450}
}