Instructions to use TeslaYang123/TC-Light with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TeslaYang123/TC-Light with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TeslaYang123/TC-Light", 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
Improve model card: Update pipeline tag, add library name, and detailed content
#2
by nielsr HF Staff - opened
This PR significantly enhances the model card for TC-Light by:
- Updating the
pipeline_tagfromimage-to-imagetovideo-to-videoto accurately reflect its core functionality in video processing and ensure better discoverability on the Hub (https://huggingface.co/models?pipeline_tag=video-to-video). - Adding
library_name: diffusersas the model's underlying components and dependencies align with the Diffusers library, which enables better integration and a "how to use" widget on the model page. - Expanding the model card content using the comprehensive information from the official GitHub repository, including detailed explanations of the method, usage instructions, examples, behavioral insights, and a proper citation. This provides a more informative and user-friendly experience for anyone visiting the model page.
TeslaYang123 changed pull request status to merged