app.py

import gradio as gr
import numpy as np
import random
import spaces #[uncomment to use ZeroGPU]
from diffusers import DiffusionPipeline , DPMSolverMultistepScheduler
import torch
from huggingface_hub import login
import os 
a=os.getenv('key_for_man_asshole')
login(token=a )
use_karras_sigmas=True

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "black-forest-labs/FLUX.1-dev"  # Replace to the model you would like to use

if torch.cuda.is_available():
    torch_dtype = torch.float16
else:
    torch_dtype = torch.float32

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)

pipe.load_lora_weights("artificiallover0/man_asshole")
pipe.fuse_lora()
pipe = pipe.to(device)
print(pipe.scheduler.compatibles)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024


@spaces.GPU #[uncomment to use ZeroGPU]
def infer(
    prompt,
    negative_prompt,
    seed,
    randomize_seed,
    width,
    height,
    guidance_scale,
    num_inference_steps,
    progress=gr.Progress(track_tqdm=True),
):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

    generator = torch.Generator().manual_seed(seed)

    image = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).images[0]

    return image, seed


examples = [
    """a naked hairy man kneeling on all fours with his dirty feet facing the viewer

    dirty feet, big hands holding his butt

    he is crowd surfing

    the crowd has their hands on him passing him forward

    he legs rest on their shoulders

    people below him are cheering

    big erect penis""",
    """Photograph of a plus-sized ginger man kneeling with his butt facing the viewer.  he has a large belly

    he has a hairy butt, big low hanging testicles and dirty unwashed bare feet

    high quality, fashion photography

    he is eating corn from a metal trough

    in a barn

    he is eating from the metal bin like a pig""",
    """Photograph of a huge muscle  man kneeling with his butt facing the viewer.

    he has a hairy butt, big low hanging testicles and dirty unwashed bare feet

    high quality, fashion photography

    he is laying face down on a red leather fainting couch""",
    """
    8k resolution, ultra detailed, 1 chico , Alone, huge muscle man
    , man in mechanic naked, ultra detailed piernas gorditas y peludas, futurist,
    with his ass in a sexual pose, asshole , military hat, looking over shoulder,
    bending down, back towards viewer, big body, fit body, not fat, gigantic buttocks,
    looking over shoulder, bending down,
    back towards viewer  whole body, sexy round hairy ass butt, thigh show, Super detailed""",

    """a chunky naked plumber kneeling under a sink holding a wrench and fixing a metal pipe under the sink.
    he looking over shoulder, bending down, back towards viewer, big body,
    His exposed anus and big testicles are the focus of the image, rear view,
    facing away from viewer, ass in viewers face, greasy, (huge:1.9) muscle man ,
    (huge:1.9)  hairy back, leather boots, plumbers crack, ((dirty sweatpants pulled down:1.9))  view from below""",
    
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # Text-to-Image Gradio Template")

        with gr.Row():
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
                 lines=5,
            )

            run_button = gr.Button("Run", scale=0, variant="primary")

        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                visible=False,
            )

            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )

            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)

            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,  # Replace with defaults that work for your model
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,  # Replace with defaults that work for your model
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=10.0,
                    step=0.1,
                    value=7.0,  # Replace with defaults that work for your model
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=30,  # Replace with defaults that work for your model
                )

        gr.Examples(examples=examples, inputs=[prompt])
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            prompt,
            negative_prompt,
            seed,
            randomize_seed,
            width,
            height,
            guidance_scale,
            num_inference_steps,
        ],
        outputs=[result, seed],
    )

if __name__ == "__main__":
    demo.launch()