Instructions to use HorizonRobotics/RoboTransfer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use HorizonRobotics/RoboTransfer 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("HorizonRobotics/RoboTransfer", 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
Add pipeline tag to improve discoverability
#1
by nielsr HF Staff - opened
Hi! I'm Niels from the Hugging Face community team.
I've opened this PR to add the image-to-video pipeline tag to your model card's metadata. This helps users discover your model when filtering for video generation tasks on the Hugging Face Hub. I've also kept the existing library name and license metadata.
nemo04 changed pull request status to merged