Instructions to use zai-org/CogVideoX-5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zai-org/CogVideoX-5b with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zai-org/CogVideoX-5b", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
sora like quality
#6
by TheBigBlockPC - opened
This video generation model performs exceptionally well, demonstrating strong generalization and impressive motion consistency. It handles a variety of 2D styles, including anime and photorealistic styles, with remarkable accuracy, avoiding the common issue of artifact generation. The model also excels in scenarios where other open-source models often struggle, making it a standout choice for high-quality video creation.