---
type: "raw_signal"
id: "iris-3b-is-a-3b-pixel-space-text-738cc1"
slug: "iris-3b-is-a-3b-pixel-space-text-738cc1"
title: "Iris-3B is a 3B pixel-space text-to-image diffusion transformer released under Apache 2.0 by Speridlabs."
description: "Speridlabs has released Iris-3B, a 3-billion-parameter pixel-space diffusion model, under Apache 2.0."
retrieval_nugget: "Speridlabs has released Iris-3B, a 3-billion-parameter pixel-space diffusion model, under Apache 2.0."
observed_at: "2026-10-12"
record_date: "2026-10-12"
date_kind: "observed_at"
why_it_matters: "Speridlabs has released Iris-3B, a 3-billion-parameter pixel-space diffusion model, under Apache 2.0. Its model card says it generates images directly at the pixel level rather than using a VAE and latent space, and that fine-tuned versions support monocular depth estimation, image restoration, and upscaling. The repository also includes Iris-3B Turbo, a four-step distilled version; the authors re"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "huggingface.co"
topics: []
entities: ["Speridlabs","Iris-3B","Iris-3B Turbo","Hugging Face"]
related_patterns: ["generative-media-becomes-application-infrastructure"]
source_url: "https://huggingface.co/speridlabs/iris-3b"
source_urls: ["https://huggingface.co/speridlabs/iris-3b"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:iris-3b-is-a-3b-pixel-space-text-738cc1"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/iris-3b-is-a-3b-pixel-space-text-738cc1/","markdown":"https://newruntime.com/signals/iris-3b-is-a-3b-pixel-space-text-738cc1.md","json":"https://newruntime.com/signals/iris-3b-is-a-3b-pixel-space-text-738cc1.json"}
---

# Iris-3B is a 3B pixel-space text-to-image diffusion transformer released under Apache 2.0 by Speridlabs.

## Retrieval answer

Speridlabs has released Iris-3B, a 3-billion-parameter pixel-space diffusion model, under Apache 2.0.

Speridlabs has released Iris-3B, a 3-billion-parameter pixel-space diffusion model, under Apache 2.0. Its model card says it generates images directly at the pixel level rather than using a VAE and latent space, and that fine-tuned versions support monocular depth estimation, image restoration, and upscaling. The repository also includes Iris-3B Turbo, a four-step distilled version; the authors report about 0.7 seconds for a 1024×1024 image on one H100. The card lists approximately 12 GB for text-to-image weights and says inference requires an NVIDIA GPU with CUDA. These are release-page descriptions and author-reported figures, not independent evaluations. Source: https://huggingface.co/speridlabs/iris-3b

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)