import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("eramth/asian-flux-4bit", torch_dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]A Flux model for asian portrait with 4bit transformer and T5 encoder.
Usage
pip install bitsandbytes
from diffusers import FluxPipeline
import torch
pipeline = FluxPipeline.from_pretrained("eramth/asian-flux-4bit",torch_dtype=torch.float16).to("cuda")
# This allows you to generate higher resolution images without much extra VRAM usage.
pipeline.vae.enable_tiling()
image = pipeline(prompt="a cute cat",num_inference_steps=25,guidance_scale=3.5).images[0]
image
- Downloads last month
- 11
Model tree for eramth/asian-flux-4bit
Base model
black-forest-labs/FLUX.1-dev