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
CogVideo
Can someone tell me how do you install this CogvideoX ? I'm not talking about any model in particular but I just want an explanation of how to get things running on comfyUI. Please do remember, the entire world isn't from a coding/programming background, so it would be very nice if this could be explained in a way a layman or a graphic designer could understand.
get comfyui, get comfyui manager. once both are working drag the JSON workflow from anyone's link, including the /examples/json stuff in the main directory.
Once dragged into the window it will show the squares with a ton of red boxes, click the mod manager you installed there is a menu button now, click find missing nodes, install, reboot, voila.
Once you reload the same workflow the red errors should go away. done!