metadata
pipeline_tag: text-to-image
FLUX.1-schnell - Onnx Olive DirectML Optimized
Original Model
https://huggingface.co/black-forest-labs/FLUX.1-schnell
Note on Float16 Conversion:
The Float16 conversion of this model is not yet perfect, and there is a noticeable quality difference compared to the ONNX Float32 version. While it still produces fantastic images, we are actively working on improving the precision of this model.
We welcome any community assistance or input regarding this conversion.
C# Inference Demo
https://github.com/TensorStack-AI/OnnxStack
// Create Pipeline
var pipeline = FluxPipeline.CreatePipeline("D:\\Models\\Flux_schnell-f32-onnx");
// Prompt
var promptOptions = new PromptOptions
{
Prompt = "Illustrate a fierce barbarian man, with muscles rippling and wielding a massive axe, roaring in triumph"
};
// Scheduler Options
var schedulerOptions = pipeline.DefaultSchedulerOptions with
{
GuidanceScale = 0f,
InferenceSteps = 4,
SchedulerType = SchedulerType.FlowMatchEulerDiscrete,
};
// Run pipeline
var result = await pipeline.GenerateImageAsync(promptOptions, schedulerOptions);
// Save Image Result
await result.SaveAsync("Result.png");
Inference Result
