import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("adamdad/videocrafterv2_diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Videocrafterv2 Diffusers
We convert the original VideoCraft2 checkpoint (available at https://github.com/AILab-CVC/VideoCrafter) to the diffusers format, which offers a more flexible inference pipeline and improved memory efficiency.
- Downloads last month
- 19
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support