OnnxStack.Core 0.1.0

OnnxStack

ONNX Runtime Projects for .NET Applications

Hardware Requirements

You can choose between Cpu and DirectML(GPU) for inference, Other Microsoft.ML.OnnxRuntime.* executors like Cuda may work but are untested

Cpu > 12GB RAM

DirectML > 10GB VRAM

ONNX Model Download

You will need an ONNX compatible model to use, Hugging Face is a great place to download the Stable Diffusion models

Download the ONNX Stable Diffusion models from Hugging Face.

• Stable Diffusion Models v1.4
• Stable Diffusion Models v1.5

Once you have selected a model version repo, click Files and Versions, then select the ONNX branch. If there isn't an ONNX model branch available, use the main branch and convert it to ONNX. See the ONNX conversion tutorial for PyTorch for more information.

Clone the model repo:

git lfs install
git clone https://huggingface.co/runwayml/stable-diffusion-v1-5 -b onnx

Projects

OnnxStack.StableDiffusion

Inference Stable Diffusion with C# and ONNX Runtime

Prompt

Stable Diffusion models take a text prompt and create an image that represents the text.

Example:

High-fashion photography in an abandoned industrial warehouse, with dramatic lighting and edgy outfits, detailed clothing, intricate clothing, seductive pose, action pose, motion, beautiful digital artwork, atmospheric, warm sunlight, photography, neo noir, bokeh, beautiful dramatic lighting, shallow depth of field, photorealism, volumetric lighting, Ultra HD, raytracing, studio quality, octane render

Negative Prompt

A negative prompt can be provided to guide the inference to exclude in calculations

Example:

painting, drawing, sketches, monochrome, grayscale, illustration, anime, cartoon, graphic, text, crayon, graphite, abstract, easynegative, low quality, normal quality, worst quality, lowres, close up, cropped, out of frame, jpeg artifacts, duplicate, morbid, mutilated, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, glitch, deformed, mutated, cross-eyed, ugly, dehydrated, bad anatomy, bad proportions, gross proportions, cloned face, disfigured, malformed limbs, missing arms, missing legs fused fingers, too many fingers,extra fingers, extra limbs,, extra arms, extra legs,disfigured,

Schedulers

Many different scheduler algorithms can be used for this computation, each having its pro- and cons. So far OnnxStack.StableDiffusion as included LMSScheduler and EulerAncestralScheduler options with more in the works.

Example: | LMSScheduler | EulerAncestralScheduler| | :--- | :--- | <img src="https://i.imgur.com/osoEqGk.png" width="256" height="256" alt="Image of browser inferencing on sample images."/> | <img src="https://i.imgur.com/Xs30KgJ.png" width="256" height="256" alt="Image of browser inferencing on sample images."/> |

 Seed: 624461087     GuidanceScale: 8     NumInferenceSteps: 30

More information and Examples can be found in the OnnxStack.StableDiffusion project README

OnnxStack.ImageRecognition

Image recognition with ResNet50v2 with C# and ONNX Runtime

~WIP~

OnnxStack.ObjectDetection

Object detection with Faster RCNN Deep Learning with C# and ONNX Runtime

~WIP~

Contribution

We welcome contributions to OnnxStack! If you have any ideas, bug reports, or improvements, feel free to open an issue or submit a pull request.

Resources

• ONNX Runtime C# API Doc
• Get Started with C# in ONNX Runtime
• Hugging Face Stable Diffusion Blog