How to use ManyWayne/Wan2.1_14B_fp8_OmniX with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("DFloat11/Wan2.1-T2V-14B-Diffusers-DF11", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ManyWayne/Wan2.1_14B_fp8_OmniX") prompt = "-" image = pipe(prompt).images[0]
Download them in the Files & versions tab.
Base model
