How to use nvidia/AnyFlow-Wan2.1-T2V-14B-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("nvidia/AnyFlow-Wan2.1-T2V-14B-Diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
Would this be compatible with the WAN VACE module for further and broader functionality? The FAR variant probably not but the normal T2V maybe?
· Sign up or log in to comment
