import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("NickKolok/lametta-v2012-beastboost-2ch-fp16", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Lametta boosted with BeastBoost
Brought to you not by me, but by Anonymous.
Should be coherent on 1024x1024 without HRfix. But nothing is guaranteed!
BeastBoost is a trick developed by Anonymous on 2ch.hk/ai/ imageboard. During BeastBoost, an additional coherence mixin is extracted from the Furry model and added to the target model.
- Downloads last month
- 7