Instructions to use TensorStack/Wan2.1-T2V-1.3B-ts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TensorStack/Wan2.1-T2V-1.3B-ts with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TensorStack/Wan2.1-T2V-1.3B-ts", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
metadata
pipeline_tag: text-to-video
Wan2.1-T2V-1.3B-ts
Original model: https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B
Model repository for TensorStack library and the windows Diffuse application
C# Inference Demo
// Pipeline Config
var pipelineConfig = new PipelineConfig
{
Path = "TensorStack/Wan2.1-T2V-1.3B-ts",
Pipeline = "WanPipeline",
ProcessType = ProcessType.TextToVideo,
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 = 832,
Height = 480,
GuidanceScale = 3f,
Scheduler = SchedulerType.FlowMatchEulerDiscrete
};
// Generate
var response = await pythonPipeline.GenerateAsync(options);
// Save Video
var fps = 16;
await response
.AsVideoTensor(fps)
.SaveAsync("Result.mp4");
}