# Stability-AI/sd3.5

Repository: https://github.com/Stability-AI/sd3.5
Canonical: https://ross.abutalabs.com/products/sd35
Language: Python
License: MIT
License Family: permissive
Last push: 2025-01-08T14:05:05+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 49
- inputs: {"age_days": 694, "days_push": 602, "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 1529, forks 149 (observed 2026-08-28T04:04:58.706885+00:00)

## What it is
A minimal inference-only reference implementation of Stable Diffusion 3.5 and SD3, including text encoders, VAE decoder, MM-DiT core, and SD3.5 Large ControlNets. It is intended to help partner organizations integrate SD3.5/SD3 inference rather than serve as an end-user tool.

## Use cases
- run stable diffusion 3.5 inference in python
- generate images from text prompts with sd3.5
- integrate sd3.5 into my own application
- use controlnets with stable diffusion 3.5 large
- reference implementation of mm-dit text-to-image model
- run sd3 medium locally

## When to choose
- you need a minimal, readable reference implementation of SD3.5/SD3 inference
- you are building your own pipeline or product on top of SD3.5 and want reference code
- you want to experiment with SD3.5 Large ControlNets directly in Python

## When to avoid
- you want a full-featured UI or workflow tool for image generation (use ComfyUI instead)
- you need training or fine-tuning code for SD3.5
- you want a maintained library with broad community support and frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, llm-inference, image-processing
- domain: artificial-intelligence, machine-learning, image-processing
- platform: python, cross-platform
- tags: stable-diffusion, text-to-image, diffusion-models, inference, controlnet, generative-ai, gpu

## Member repositories
- Stability-AI/sd3.5 (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:58.706885+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 2026-08-30T04:31:27.223192+00:00, confidence not recorded.
  - readme: https://github.com/Stability-AI/sd3.5 (fetched 2026-08-28T04:04:58.706885+00:00, sha 21c5fa2fd0a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.