Instructions to use vidfom/Wav2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use vidfom/Wav2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("vidfom/Wav2", torch_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
| from PIL import ImageEnhance | |
| from .base import VideoProcessor | |
| class ContrastEditor(VideoProcessor): | |
| def __init__(self, rate=1.5): | |
| self.rate = rate | |
| def from_model_manager(model_manager, **kwargs): | |
| return ContrastEditor(**kwargs) | |
| def __call__(self, rendered_frames, **kwargs): | |
| rendered_frames = [ImageEnhance.Contrast(i).enhance(self.rate) for i in rendered_frames] | |
| return rendered_frames | |
| class SharpnessEditor(VideoProcessor): | |
| def __init__(self, rate=1.5): | |
| self.rate = rate | |
| def from_model_manager(model_manager, **kwargs): | |
| return SharpnessEditor(**kwargs) | |
| def __call__(self, rendered_frames, **kwargs): | |
| rendered_frames = [ImageEnhance.Sharpness(i).enhance(self.rate) for i in rendered_frames] | |
| return rendered_frames | |