# vladmandic/sdnext

SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing

Repository: https://github.com/vladmandic/sdnext
Canonical: https://ross.abutalabs.com/products/sdnext
Homepage: https://vladmandic.github.io/sdnext/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: sdnext, ai-art, caption, diffusers, generative-art, python, pytorch, stable-diffusion, transformers, webui
Last push: 2026-08-26T23:47:06+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 96
- inputs: {"age_days": 1348, "days_push": 7, "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 7320, forks 579 (observed 2026-08-28T04:09:58.193527+00:00)

## What it is
SD.Next is an open-source, self-hosted WebUI server application for AI generative image and video creation built on Stable Diffusion and Diffusers. It supports dozens of diffusion models with features like on-the-fly quantization, CPU/GPU memory balancing, captioning with LLM/VLM models, and image processing tools.

## Use cases
- generate images with stable diffusion models
- generate ai videos from text prompts
- caption images automatically with vision language models
- upscale and enhance ai-generated images
- run large diffusion models on limited vram with quantization
- self-host an ai art generation web interface
- interrogate and tag images with models like deepdanbooru

## When to choose
- you want a feature-rich self-hosted WebUI for stable diffusion image and video generation
- you need to run diffusion models on limited VRAM via quantization and offloading
- you want built-in captioning, tagging, and image processing alongside generation
- you need cross-platform support including AMD, Intel, and Apple GPUs

## When to avoid
- you need a lightweight programmatic library rather than a full web application
- you want a simple one-command image generator without a UI
- you only need text-only LLM inference without image generation

## Facets
- artifact type: application
- maturity: active
- function: image-processing, machine-learning, llm-inference, ui-components, self-hosted
- domain: artificial-intelligence, image-processing, deep-learning, media
- platform: python, cross-platform, self-hosted
- tags: stable-diffusion, diffusers, webui, ai-art, generative-art, captioning, upscaling, pytorch, model-quantization, video, web-server, gpu

## Member repositories
- vladmandic/sdnext (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:58.193527+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 2026-08-29T17:38:39.835740+00:00, confidence not recorded.
  - readme: https://github.com/vladmandic/sdnext (fetched 2026-08-28T04:09:58.193527+00:00, sha ce4fc6c8f346)
  - homepage: https://vladmandic.github.io/sdnext/ (fetched 2026-08-29T08:34:02.798563+00:00, sha f95e898a9fe8)
- Data as of 2026-08-30T08:39:29.467469+00:00.