CogVideoX-2B - Install Locally to Create Videos from Text

 This video shows how to locally install CogVideoX-2B which is an open-source video generation model.

Code:

conda create -n cog python=3.11 -y && conda activate cog

git clone https://github.com/THUDM/CogVideo.git && CogVideo

pip install -r requirements.txt

pip install --upgrade opencv-python transformers diffusers

conda install jupyter -y

pip uninstall charset_normalizer -y

pip install charset_normalizer

jupyter notebook

import torch

from diffusers import CogVideoXPipeline

from diffusers.utils import export_to_video

prompt = "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, casting a gentle glow on the scene."

pipe = CogVideoXPipeline.from_pretrained(

    "THUDM/CogVideoX-2b",

    torch_dtype=torch.float16

)

pipe.enable_model_cpu_offload()

prompt_embeds, _ = pipe.encode_prompt(

    prompt=prompt,

    do_classifier_free_guidance=True,

    num_videos_per_prompt=1,

    max_sequence_length=226,

    device="cuda",

    dtype=torch.float16,

)

video = pipe(

    num_inference_steps=50,

    guidance_scale=6,

    prompt_embeds=prompt_embeds,

).frames[0]

export_to_video(video, "output.mp4", fps=8)