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("mirav/newmoon", dtype=torch.bfloat16, device_map="cuda")

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

If you like my work, consider supporting me.
NewMoon: Soft, bright colors.
ChamomileTea: Darker, moodier colors.
TestMoon: Alternate style. Very cute, but a bit flawed.
NewMoonTest2A: Alternate style. Soft, flat, and cute, but harder to work with.
newmoon.yaml: sample prompt for animatediff NewMoon_clip_l.safetensors: Extracted CLIP for advanced model merging.

Downloads last month
54
Safetensors
Model size
0.9B params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Spaces using mirav/newmoon 9