One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models
Paper • 2505.21960 • Published • 5
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("senmaonk/loopfree-sd2.1-base", 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 contains the Loopfree model presented in One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models. Loopfree is a distilled T2I model which allows fast image generation.
More information regarding the code and architecture can be found at: https://github.com/sen-mao/Loopfree
- Downloads last month
- 3