import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SenecaCicero/LCM_RealisticVision_V5.0_noVAE", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]LCM_Realistic Vision_V5.0_noVAE
A Stable Diffusion 1.5 realism model, converted to LCM, that can generate images in as little as 6 steps.
Very useful for quickly generating images for concept/sketch design purposes - or anything else that takes your fancy.
More details on LCM: https://latent-consistency-models.github.io/
Original Realistic Vision V5.0 is available here: https://huggingface.co/SG161222/Realistic_Vision_V5.1_noVAE
Coverted to LCM with this script: https://github.com/vladmandic/automatic/blob/master/cli/lcm-convert.py
- Downloads last month
- -