# Stability-AI/generative-models

Generative Models by Stability AI

Repository: https://github.com/Stability-AI/generative-models
Canonical: https://ross.abutalabs.com/products/generative-models
Language: Python
License: MIT
License Family: permissive
Last push: 2025-12-16T08:36:18+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 57, release rhythm 8, longevity 83
- inputs: {"age_days": 1169, "days_push": 260, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 27271, forks 3101 (observed 2026-08-28T04:11:47.629768+00:00)

## What it is
Stability AI's official repository of generative diffusion models, including Stable Diffusion, Stable Video, and SV4D 2.0 for image, video, and 4D asset generation. It provides model definitions, training, and sampling scripts for research use.

## Use cases
- generate images from text prompts with stable diffusion
- generate novel-view videos from a single input video
- create 4D assets from video of a moving object
- run diffusion model inference on GPU
- research and fine-tune generative models
- sample videos from pretrained checkpoints

## When to choose
- you want official Stability AI model implementations and sampling scripts
- you need video-to-4D or novel-view video synthesis
- you are doing research with diffusion models in Python

## When to avoid
- you want a polished end-user UI for image generation (use ComfyUI or Automatic1111 instead)
- you need production deployment rather than research code
- you lack a CUDA GPU

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, video-processing, stable-diffusion, gpu-computing
- domain: deep-learning, machine-learning, artificial-intelligence, image-processing
- platform: python, cli
- tags: diffusion-models, text-to-image, video-generation, 4d-generation, generative-ai, stability-ai, research-code, video, gpu, linux

## Member repositories
- Stability-AI/generative-models (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:47.629768+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 2026-08-29T16:54:33.680848+00:00, confidence not recorded.
  - readme: https://github.com/Stability-AI/generative-models (fetched 2026-08-28T04:11:47.629768+00:00, sha 65b7bfb4cbce)
- Data as of 2026-08-30T08:39:29.467469+00:00.