How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Yntec/MGM", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

MGM

This model with the zVAE baked in.

Sample and prompt:

Sample

pretty cute little girl in tricycle, Screenshot of an surreal light pink 70s round minimalist architecture, Sharp, 35mm still from a sci fi blockbuster color movie made in 2022, beautiful portrait, Dorothy, set in 1860, in front of a spaceship that has just landed on an alien planet, a robot stands nearby, are all wearing

Original page: https://civitai.com/models/109568/mgmv1

Version without VAE: https://huggingface.co/digiplay/MGM

Downloads last month
19
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Spaces using Yntec/MGM 57