vladmandic/sdnext
SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing
Supports 150+ OpenCLIP models and 20+ vision language models for image captioning and interrogation. Features cross-platform GPU acceleration (CUDA, ROCm, DirectML, OpenVINO, ZLUDA, Intel Arc) with automatic hardware detection, plus advanced optimization backends like Triton and quantization methods including BitsAndBytes and LayerWise. Built-in dependency management and auto-updates enable seamless deployment across Windows, Linux, macOS, and containerized environments.
6,987 stars. Actively maintained with 362 commits in the last 30 days.
Stars
6,987
Forks
555
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
362
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/vladmandic/sdnext"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
appolloqin/gen-txt-to-image
一款文生视频应用，用于小说推文，生成漫画等视频。使用主流大模型，结合Stable Diffusion，实现文生图，图生视频本地化私有部署。
ThereforeGames/unprompted
Templating language written for Stable Diffusion workflows. Available as an extension for the...
PR0CK0/StableDiffusionEndToEndGuide
An End-to-End Guide for Learning Stable Diffusion - From Noob to Expert