FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
Paper • 2502.05179 • Published • 24
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("FoundationVision/FlashVideo", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]FlashVideo
This repository contains the weights for the model described in the paper FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation.
Project page: https://jshilong.github.io/flashvideo-page/
- Downloads last month
- -