README.md

metadata

license: other
language:
  - en
base_model:
  - black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
library_name: diffusers
tags:
  - art

I trained this model using the Diffusers library by randomly selecting layers and blocks (not training every layer), which reduced the training time and is expected to yield better results.

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("kpsss34/FHDR_Uncensored", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "a women..."
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.0,
    num_inference_steps=40,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0]
image.save("outputs.png")