Image generationComputer vision

Iris-3B

Generates images directly in pixels, without a compressed latent space. After fine-tuning, the same weights estimate depth from a single photo and restore and upscale images 4 times. Prompts are in English, the default size is 1024 by 1024.

Developer
Sperid Labs, not stated
First release
Oct 2026
Latest release
Oct 2026
Sizes
3B
License
Commercial use allowedApache 2.0
Running
On your own serverNeeds a GPU
Industries
Media and production, Marketing and content, Retail and marketplaces, Science and research
Deploy on your server Hugging Face

What it does

  • generating images from a description
  • estimating scene depth from a single photo
  • restoring and upscaling old or compressed photos

Where it is used

marketing and contentonline stores and catalogscomputer vision research

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Iris-3B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Iris-3B be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Iris-3B need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Iris-3B support Russian?

Language does not matter for this model: it does not work with text.

Where can I download Iris-3B and what does it cost?

The Iris-3B weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Image generationQwen-ImageAlibaba · ChinaCommercial use with conditions

Image generation and editing, including text in images. Earlier versions allow commercial use; the latest 2.1 is non-commercial only.

DetailsImage generationFLUXBlack Forest Labs · GermanyCommercial use with conditions

Image generation from the creators of Stable Diffusion. Renders text in images well and keeps the composition.

DetailsComputer visionDepth AnythingByteDance and the University of Hong Kong · ChinaCommercial use with conditions

Estimates depth, the distance to every point, from one ordinary photo or video. DA3 reconstructs scene geometry from several frames.

Details

Source: huggingface.co/speridlabs/iris-3b. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.