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
15
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for newgenai79/flux-4bit

Finetuned
(354)
this model