app.py

import gradio as gr
import numpy as np
import random

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AI-B/UTENA-7B-NSFW-V2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AI-B/UTENA-7B-NSFW-V2")
model = AutoModelForCausalLM.from_pretrained("AI-B/UTENA-7B-NSFW-V2")

# @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),
):
   

    
    demo.launch()