import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Mobius-labs/emoji_model_msfluentui", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Background
This model was trained to generate emojis! By nature, the outputs are simplified but are meant to capture the essence of their subjects.
The model is good at depicting people and animals. Abstract faces (e.g. smiley/sad faces) aren’t consistent at the moment, but can likely be fixed in future versions.
Join our Discord for any questions or feedback!
Resources
- Downloads last month
- 5