Instructions to use TensorStack/Qwen-Image-ts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TensorStack/Qwen-Image-ts with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TensorStack/Qwen-Image-ts", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| pipeline_tag: image-to-image | |
| # Qwen-Image-ts | |
| Original model: https://huggingface.co/Qwen/Qwen-Image | |
| Model repository for `TensorStack` library and the windows `Diffuse` application | |
| ## C# Inference Demo | |
| ```csharp | |
| // Pipeline Config | |
| var pipelineConfig = new PipelineConfig | |
| { | |
| Path = "TensorStack/Qwen-Image", | |
| Pipeline = "QwenImagePipeline", | |
| ProcessType = ProcessType.ImageToImage, | |
| IsFullOffloadEnabled = true, | |
| DataType = DataType.Bfloat16 | |
| }; | |
| // Create Pipeline | |
| using (var pythonPipeline = new PythonPipeline(pipelineConfig, PipelineProgress.ConsoleCallback)) | |
| { | |
| // Download/Load Model | |
| await pythonPipeline.LoadAsync(); | |
| // Generate Option | |
| var options = new PipelineOptions | |
| { | |
| Prompt = "Cute doggo riding a bicycle", | |
| Steps = 30, | |
| Width = 1024, | |
| Height = 1024, | |
| GuidanceScale = 4f, | |
| Scheduler = SchedulerType.FlowMatchEulerDiscrete, | |
| ImageInput = new ImageInput("Image.png") | |
| }; | |
| // Generate | |
| var response = await pythonPipeline.GenerateAsync(options); | |
| // Save Image | |
| await response | |
| .AsImageTensor() | |
| .SaveAsync("Result.png"); | |
| } | |
| ``` | |