Usage:

πŸ“‚ infer_dir/
└── generate_quant_flux2.py
└── πŸ“‚ local_model/
    β”‚   β”œβ”€β”€ pipeline_config.json
    β”‚   └── scheduler
    β”‚   └── text_encoder
    β”‚   └── tokenizer
    β”‚   └── transformer
        └── vae
import os
import torch
from generate_quant_flux2 import load_pipeline

pipe = load_pipeline("./local_model", "cuda")

prompt = ("A asian woman with red accent stripe features padded straps, brand logo, and multiple compartments, with a built-in LED light for low-light visibility.")

seed = 0
img = pipe(
    prompt=prompt,
    num_inference_steps=4,
    guidance_scale=1.0,
    generator=torch.Generator("cpu").manual_seed(seed),
).images[0]

os.makedirs("outputs", exist_ok=True)
path = f"img_s{seed}.png"
img.save(path)
print("saved", path)

content

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for kpsss34/klein-4B-3BIT-SFW

Finetuned
(79)
this model

Collection including kpsss34/klein-4B-3BIT-SFW