How to use WMSD/World-Model-Self-Distillation with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WMSD/World-Model-Self-Distillation", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
This repository will host the model weights for World Model Self-Distillation: Training World Models to Solve General Tasks.
Weights, loading instructions, and model details will be added later.
