Instructions to use huaichang/PersonaLive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use huaichang/PersonaLive with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("huaichang/PersonaLive", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Improve model card: Add pipeline tag, library name, paper/code/project links, and citation
#4
by nielsr HF Staff - opened
This PR improves the model card for PersonaLive! by:
- Adding
pipeline_tag: image-to-videoto the YAML metadata to correctly categorize the model and enhance discoverability on the Hugging Face Hub. - Adding
library_name: diffusersto the YAML metadata. This enables the automated "how to use" code snippet, as the model demonstrates compatibility with components often used in the Diffusers library (e.g.,sd-image-variations-diffusers,sd-vae-ft-mse). - Adding explicit links to the paper (PersonaLive! Expressive Portrait Image Animation for Live Streaming), the code repository (GitHub), and the project page (huai-chang.github.io) at the top of the model card content for easier access.
- Uncommenting and correctly displaying the BibTeX citation section, which was present but hidden in the original model card.
Please review and merge this PR if everything looks good.
huaichang changed pull request status to merged
Thank you for your contribution!