Instructions to use zai-org/CogVideoX-5b-I2V with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zai-org/CogVideoX-5b-I2V 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("zai-org/CogVideoX-5b-I2V", 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
Is 2B-I2V model coming?
#7
by MikeT4 - opened
Hi, I'm curious if the 2B model for image to video is planned to be released? 2B is much more convenient for sandbox runs
thanks!
We haven’t trained the 2B I2V model, and we didn’t use RoPE embeddings, so we didn’t open-source it because the model hasn’t been trained.