oracle/sd4j
Stable diffusion pipeline in Java using ONNX Runtime
Implements txt2img generation with negative prompt support and configurable diffusion schedulers, packaged as both a Swing GUI and embeddable Java library. Targets multiple model architectures (SD v1.5, v2, SDXL) with automatic version detection, and supports hardware acceleration via CUDA, CoreML, and DirectML backends through ONNX Runtime's execution providers. Built as a reference implementation demonstrating ONNX Runtime Java API best practices and performance optimization patterns.
176 stars.
Stars
176
Forks
21
Language
Java
License
UPL-1.0
Category
Last pushed
Jan 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/oracle/sd4j"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
leejet/stable-diffusion.cpp
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
xlite-dev/lite.ai.toolkit
🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion,...
MochiDiffusion/MochiDiffusion
Run Stable Diffusion on Mac natively
ssube/onnx-web
web UI for GPU-accelerated ONNX pipelines like Stable Diffusion, even on Windows and AMD
xororz/local-dream
Run Stable Diffusion on Android Devices with Snapdragon NPU acceleration. Also supports CPU/GPU...