# Stability-AI/StableCascade

Official Code for Stable Cascade

Repository: https://github.com/Stability-AI/StableCascade
Canonical: https://ross.abutalabs.com/products/stablecascade
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2024-07-25T11:54:13+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 67
- inputs: {"age_days": 951, "days_push": 769, "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 6540, forks 510 (observed 2026-08-28T04:09:45.053526+00:00)

## What it is
Official codebase for Stable Cascade, a text-to-image generation model built on the Würstchen architecture with a highly compressed latent space for faster inference and cheaper training. It provides training and inference scripts for Stage A/B/C models, including finetuning, LoRA, and ControlNet support.

## Use cases
- generate images from text prompts
- train a text-to-image diffusion model
- finetune an image generation model with LoRA
- run fast image generation inference on GPU
- add ControlNet conditioning to image generation
- compare text-to-image model quality and speed

## When to choose
- you need efficient text-to-image generation with faster inference than Stable Diffusion
- you want to train or finetune an image generation model with lower compute cost
- you need official reference code for the Würstchen/Stable Cascade architecture

## When to avoid
- you need a production-ready image generation service with an API
- you require broad ecosystem tooling like ComfyUI or Automatic1111 integrations
- you lack a GPU or want CPU-only inference

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, llm-inference, llm-training
- domain: deep-learning, image-processing, artificial-intelligence
- platform: python
- tags: text-to-image, diffusion-model, image-generation, stable-diffusion, generative-ai, jupyter-notebook, gpu

## Member repositories
- Stability-AI/StableCascade (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:45.053526+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 2026-08-29T17:44:06.838888+00:00, confidence not recorded.
  - readme: https://github.com/Stability-AI/StableCascade (fetched 2026-08-28T04:09:45.053526+00:00, sha 149f1b7f4de9)
- Data as of 2026-08-30T08:39:29.467469+00:00.