amd/stable-diffusion-xl-1.0_io32_amdgpu

Stable-Diffusion XL Base 1.0 - AMD Optimized ONNX

Original Model

https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0

_io32/16

_io32: model input is fp32, model will convert the input to fp16, perform ops in fp16 and write the final result in fp32

_io16: model input is fp16, perform ops in fp16 and write the final result in fp16

Running

1. Using Amuse GUI Application

Use Amuse GUI application to run it: https://www.amuse-ai.com/

2. C# Inference Demo

https://github.com/TensorStack-AI/OnnxStack

// csharp example
// Create Pipeline
var pipeline = StableDiffusionPipeline.CreatePipeline("D:\\Models\\stable-diffusion-xl-base-1.0_io32_amdgpu");
// Prompt
var promptOptions = new PromptOptions
{
    Prompt = "a beautiful castle in the mountains of Lake Tahoe snow, deep blue lake, ultra hd, cartoonish style"
};
// Run pipeline
var result = await pipeline.GenerateImageAsync(promptOptions, schedulerOptions);
// Save Image Result
await result.SaveAsync("Result.png");

Inference Result