Instructions to use FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree", 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
aaaa
Create a 10-second cinematic video, 16:9, with a light comedic tone.
Scene: A camel walks across a vast golden sand desert at sunset, with soft dunes stretching into the distance and warm orange light.
Action: The camel stops, rises up onto its hind legs and stands upright like a human. It holds a small traditional Arabic coffee cup (finjan) in one front hoof, sips slowly, then strikes a confident, dramatic pose. Its expression is calm and a little smug. Camera: a slow dolly-in from a medium wide shot to a low-angle close-up as it stands up.
Style: realistic, warm color grading, dust particles floating in the light, subtle wind moving the sand. Smooth natural motion. No text, no subtitles, no logos.
Audio: soft desert wind, a gentle coffee pour sound, and a light oud melody in the background.