Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation
Paper • 2412.07761 • Published
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("jxAIbot/VDM_EVFI_VIDEO", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation (CVPR 2025)
Official repository for the CVPR 2025 paper, "Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation"
This is for the model trained to insert 11 frames (generating 11 + 2 = 13 frames)
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support