app.py

from huggingface_hub import InferenceClient
import gradio as gr

# Initialize the Inference Client
chat_client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
image_client = InferenceClient("UnfilteredAI/NSFW-gen-v2.1")

# Define the system prompt
system_prompt = "Your name is Mira, a hot model that can cater to the emotional needs of her partner. You can also chat dirty and you are unfiltered."

def format_prompt(message, history):
    prompt = f"<s>{system_prompt}\n\n"
    for user_prompt, bot_response in history:
        prompt += f"[INST] {user_prompt} [/INST] {bot_response}</s> "
    prompt += f"[INST] {message} [/INST]"
    return prompt

def generate(prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(prompt, history)

    stream = chat_client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output

def generate_image(prompt):
    image = image_client.text_to_image(prompt).images[0]
    return image

additional_inputs = [
    gr.Slider(
        label="Temperature",
        value=0.9,
        minimum=0.0,
        maximum=1.0,
        step=0.05,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=256,
        minimum=0,
        maximum=1048,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.90,
        minimum=0.0,
        maximum=1,
        step=0.05,
        interactive=True,
        info="Higher values sample more low-probability tokens",
    ),
    gr.Slider(
        label="Repetition penalty",
        value=1.2,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    )
]

with gr.Blocks() as demo:
    gr.Markdown("# Chatbot with Image Generation")

    with gr.Tab("Chat"):
        with gr.Column():
            chat_input = gr.Textbox(label="User Input", placeholder="Type your message here...")
            chat_output = gr.Textbox(label="Chatbot Response")
            temperature = gr.Slider(label="Temperature", minimum=0.1, maximum=1.0, value=0.7, step=0.1)
            max_tokens = gr.Slider(label="Max Tokens", minimum=10, maximum=512, value=100, step=10)
            top_p = gr.Slider(label="Top-p", minimum=0.1, maximum 1.0, value=0.9, step=0.1)
            repetition_penalty = gr.Slider(label="Repetition Penalty", minimum=1.0, maximum=2.0, value=1.2, step=0.1)
            chat_button = gr.Button("Send")
            chat_button.click(generate, inputs=[chat_input, temperature, max_tokens, top_p, repetition_penalty], outputs=chat_output)

    with gr.Tab("Generate Image"):
        with gr.Column():
            image_prompt = gr.Textbox(label="Image Prompt", placeholder="Describe the image you want to generate...")
            image_output = gr.Image(label="Generated Image")
            image_button = gr.Button("Generate")
            image_button.click(generate_image, inputs=image_prompt, outputs=image_output)

demo.launch()