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
Commit History
-
Update README.md
Verified signaturecfce540 -
Update README.md
Verified signatureb431862
-
Add quantization examples using torchao and quanto
Verified signatureHey, I'm Aryan from the Diffusers team 👋 Congratulations on the release of CogVideoX-5B! It would be great to showcase some examples on how the quantized inference (`int8`, and other datatypes) can be run to lower memory requirements by using TorchAO and Quanto, especially since we mention it in the model card table. Feel free to modify the code/wording/URLs in whichever way you see best fit. Could we do it for the chinese README, CogVideoX-2B and CogVideo GitHub repo as well? Thanks!af6c70a -
Update transformers version (#1)
zR +1: lysandre Verified signature- Update transformers version (4b86495ffb7c44a649485c146b51c97e9737dd5b) Co-authored-by: Lysandre <lysandre@users.noreply.huggingface.co>f854f4b -
for release
zRc08ffac
-
test release
zR0105673
-
update
zR17ab7f9
-
test
zR99eaacc -
test
zRa190ef4 -
zh path
zR33b90ca -
init
Ubuntu4e56534
-
initial commit
zRVerified signature17e792a