sdxl-turbo 开源项目推荐（25 个）

siliconflow /onediff

OneDiff：开箱即用的扩散模型加速库。

Shilin-LU /VINE

[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances" (Official Implementation)

GradientSurfer /Draw2Img

一个简单的网页界面，用于交互式文本引导图像生成，适合任何年龄和技能水平。

garibida /ReNoise-Inversion

Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"

koji /AI-Colab-Notebooks

该项目在 GitHub 上没有填写描述

carllapierre /diffusion-canvas

A simple react app with a canvas to draw an image. Real time image-to-image inference using Stable Diffusion XL Turbo and Modal

AllenEdgarPoe /MirrorX-Real-time-SD-TD-SDXLora

Real-time Img2img translation! (TouchDesigner+T2Iadapter\_canny+SDXL+turbo\_LoRA)

soulteary /docker-stable-diffusion-xl-turbo

Stable Diffusion XL Turbo 实时文生图、图生图

himanshumahajan138 /Imagina-AI

Turn a single theme into a cinematic short film, a local-first pipeline that drafts the script, storyboards each scene, renders the video, and lip-syncs the voiceover, with graceful fallback to cloud providers when needed.

wajason /Nano_Cinema_AI_Video_Studio

🎬 Nano Cinema: An all-in-one local AI video production studio. Automatically orchestrates Llama-3 (Script), SDXL-Turbo (Visuals), EdgeTTS (Audio), and LTX-Video (Motion) into a seamless Python workflow. Create cinematic short films with no API fees, full privacy, and professional-grade editing logic included!!! 🚀

europanite /sdxl-container

Docker container to train SDXL LoRA adapters and run SDXL inference.

YASSER-27 /sd-turbo-original

SD Turbo Generator Images Pc , text-to-image , image-to-image , Gui

KeepSerene /sonauto-ai-music-gen-saas

Sonauto — A full-stack AI music generation SaaS. Describe your sound in plain words and walk away with a complete song — AI-written lyrics, an original melody, and unique cover artwork — all generated in minutes.

vaishak-v-nair /FrameGenX

Contract-driven text-to-image generation pipeline with multi-modal verification (GroundingDINO, CLIP, VQA), regional attention steering, closed-loop self-repair, and real-time glass-box React UI on 6GB consumer GPUs.

ChaoticByte /sdxl-cli

A very rudimentary cli for Stable Diffusion XL (Turbo) CPU inference from a local model path

hitthecodelabs /CreativeAI-Portraits

使用多个版本的 Stable Diffusion 模型生成的复杂且富有想象力的图像。

MMujtabaX /Multimodal-Vision-BLIP-Stable-Diffusion

Multimodal computer vision with Hugging Face: image captioning and VQA with BLIP, text-to-image with Stable Diffusion 1.5 and SDXL Turbo, plus prompt, guidance and step experiments.

ahmedmbutt /SD-Turbo-API

SD-Turbo API built using FastAPI and Docker and deployed on HuggingFace

Gaova777 /cuentos-a-mi-medida

Illustrated, narrated Spanish stories written at a child's measured reading level. Reproduces Adversarial Diffusion Distillation (SDXL-Turbo) on one RTX 4060.

solomon-asmr /promptBattle

Multiplayer Telegram bot where players guess AI image prompts. Built with SDXL Turbo (image generation), Jina CLIP v2 (semantic similarity), FastAPI, and Kaggle GPU.