ssube/onnx-web
web UI for GPU-accelerated ONNX pipelines like Stable Diffusion, even on Windows and AMD
Wraps HuggingFace diffusers pipelines in a REST API with background job queueing and per-pipeline accelerator selection, supporting SDXL, ControlNet, LoRA blending, multi-stage prompts, and face correction. The architecture separates a stateless API server (deployable remotely via OCI containers) from a client-side web UI, with model conversion utilities enabling checkpoint imports from Civitai and format optimization for low-memory devices. Implements advanced features like region-based prompting, infinite prompt length weighting, and panorama generation across multiple inference passes.
234 stars and 168 monthly downloads. Available on PyPI.
Stars
234
Forks
30
Language
Python
License
MIT
Category
Last pushed
Dec 02, 2025
Monthly downloads
168
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ssube/onnx-web"
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
xororz/local-dream
Run Stable Diffusion on Android Devices with Snapdragon NPU acceleration. Also supports CPU/GPU...
DarthAffe/StableDiffusion.NET
C# Wrapper for StableDiffusion.cpp