Instructions to use thu-ml/CogVideoX-RIFLEx-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use thu-ml/CogVideoX-RIFLEx-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("thu-ml/CogVideoX-RIFLEx-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
|
Download README.md from thu-ml/CogVideoX-RIFLEx-diffusers: direct link, hf CLI and curl.
- Browser
- Download file 348 Bytes
-
https://huggingface.co/thu-ml/CogVideoX-RIFLEx-diffusers/resolve/refs%2Fpr%2F1/README.md
- Command line
-
hf download hf://thu-ml/CogVideoX-RIFLEx-diffusers@refs/pr/1/README.md
-
curl -L -o README.md https://huggingface.co/thu-ml/CogVideoX-RIFLEx-diffusers/resolve/refs%2Fpr%2F1/README.md
348 Bytes
metadata
license: apache-2.0
pipeline_tag: text-to-video
library_name: diffusers
This repository contains the model described in the paper RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers.
Project page: https://riflex-video.github.io/. Code: https://github.com/thu-ml/RIFLEx