# antirez/iris.c

Flux 2 image generation model pure C inference

Repository: https://github.com/antirez/iris.c
Canonical: https://ross.abutalabs.com/products/irisc
Language: C
License: MIT
License Family: permissive
Last push: 2026-02-13T15:22:48+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 35, longevity 16
- inputs: {"age_days": 227, "days_push": 201, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1983, forks 146 (observed 2026-08-28T04:06:01.995513+00:00)

## What it is
Iris is a pure C inference pipeline that generates images from text prompts using open-weights diffusion transformer models like FLUX.2 Klein and Z-Image-Turbo. It has zero external dependencies beyond the C standard library, with optional MPS and BLAS acceleration, and requires no Python or CUDA at inference time.

## Use cases
- generate images from text prompts in C
- run flux image generation locally without python
- text-to-image inference on a macbook with mps acceleration
- generate images with no cuda or gpu toolkit required
- run diffusion transformer models with zero dependencies
- download and run open weights image models from huggingface

## When to choose
- you want dependency-free, pure C text-to-image inference
- you're on Apple Silicon and want fast MPS-accelerated image generation
- you want to avoid Python runtimes and CUDA toolkits at inference time
- you want to study or hack on a minimal diffusion model implementation in C

## When to avoid
- you need production-scale or multi-user image generation serving
- you require CUDA/NVIDIA GPU acceleration
- you need models beyond the supported FLUX.2 Klein and Z-Image-Turbo families
- you want a GUI or web interface rather than a CLI

## Facets
- artifact type: cli-tool
- maturity: active
- function: llm-inference, image-processing, cli
- domain: artificial-intelligence, image-processing, machine-learning
- platform: cli, cpp
- tags: text-to-image, diffusion-transformer, flux, pure-c, zero-dependencies, blas, mps, stable-diffusion, macos, linux

## Member repositories
- antirez/iris.c (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:01.995513+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:03:25.720603+00:00, confidence not recorded.
  - readme: https://github.com/antirez/iris.c (fetched 2026-08-28T04:06:01.995513+00:00, sha b96be93ed256)
- Data as of 2026-08-30T08:39:29.467469+00:00.