import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("newgenai79/flux-4bit", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Credits: eramth
The Flux model with 4bit transformer and T5 encoder.
Usage
from diffusers import FluxPipeline
import torch
pipe = FluxPipeline.from_pretrained("newgenai79/flux-4bit",torch_dtype=torch.float16).to("cuda:1")
pipe_kwargs = {
"prompt": "A cat holding a sign that says hello world",
"height": 1024,
"width": 1024,
"guidance_scale": 3.5,
"num_inference_steps": 50,
"max_sequence_length": 512,
}
image = pipe(**pipe_kwargs, generator=torch.manual_seed(0),).images[0]
- Downloads last month
- 14
Model tree for newgenai79/flux-4bit
Base model
black-forest-labs/FLUX.1-dev