import os import requests import subprocess import gradio as gr # Token Hugging Face từ biến môi trường hf_token = os.getenv("HF_TOKEN") # URLs cần tải app_url = "https://huggingface.co/datasets/ArrcttacsrjksX/Deffusion/resolve/main/RunModelAppp/App/sdRundeffusiononhuggingfacemaster-ac54e00" model_url = "https://huggingface.co/datasets/ArrcttacsrjksX/Deffusion/resolve/main/Model/realisticVisionV60B1_v51HyperVAE.safetensors" # Đường dẫn lưu file app_path = "sdRundeffusiononhuggingfacemaster-ac54e00" model_path = "realisticVisionV60B1_v51HyperVAE.safetensors" # Hàm tải file từ Hugging Face def download_file(url, output_path, token): headers = {"Authorization": f"Bearer {token}"} response = requests.get(url, headers=headers, stream=True) response.raise_for_status() # Kiểm tra lỗi with open(output_path, "wb") as f: for chunk in response.iter_content(chunk_size=8192): f.write(chunk) print(f"Downloaded: {output_path}") # Tải các file nếu chưa tồn tại if not os.path.exists(app_path): download_file(app_url, app_path, hf_token) subprocess.run(["chmod", "+x", app_path]) # Thay đổi quyền thực thi if not os.path.exists(model_path): download_file(model_url, model_path, hf_token) # Hàm xử lý chạy ứng dụng def run_command(prompt, mode, height, width, steps, seed, init_image=None, threads=-1, weight_type="f32", negative_prompt="", cfg_scale=7.0, strength=0.75, style_ratio=0.2, control_strength=0.9, sampling_method="euler_a", batch_count=1, schedule="discrete", clip_skip=-1, vae_tiling=False, vae_on_cpu=False, clip_on_cpu=False, control_net_cpu=False, canny=False, color=False, verbose=False, rng="cuda"): try: # Lưu ảnh đầu vào nếu được cung cấp init_image_path = None if init_image is not None: init_image_path = "input_image.png" init_image.save(init_image_path) # Tạo lệnh chạy command = [ f"./{app_path}", "-M", mode, "-m", model_path, "-p", prompt, "-H", str(height), "-W", str(width), "--steps", str(steps), "-s", str(seed), "-t", str(threads), "--type", weight_type, "--cfg-scale", str(cfg_scale), "--strength", str(strength), "--style-ratio", str(style_ratio), "--control-strength", str(control_strength), "--sampling-method", sampling_method, "--batch-count", str(batch_count), "--schedule", schedule, "--clip-skip", str(clip_skip), "--vae-tiling" if vae_tiling else None, "--vae-on-cpu" if vae_on_cpu else None, "--clip-on-cpu" if clip_on_cpu else None, "--control-net-cpu" if control_net_cpu else None, "--canny" if canny else None, "--color" if color else None, "-v" if verbose else None, "--rng", rng ] # Loại bỏ các giá trị None trong danh sách lệnh command = [arg for arg in command if arg is not None] # Thêm ảnh đầu vào nếu có if mode == "img2img" and init_image_path: command.extend(["-i", init_image_path]) # Chạy lệnh và hiển thị log theo thời gian thực process = subprocess.Popen( command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True ) logs = [] for line in process.stdout: logs.append(line.strip()) # Lưu log vào danh sách print(line, end="") # In log ra màn hình process.wait() # Đợi tiến trình hoàn thành # Kiểm tra kết quả và trả về if process.returncode == 0: output_path = "./output.png" # Đường dẫn ảnh đầu ra mặc định return output_path if os.path.exists(output_path) else None, "\n".join(logs) else: error_log = process.stderr.read() # Đọc lỗi logs.append(error_log) return None, "\n".join(logs) except Exception as e: return None, str(e) # Giao diện Gradio def toggle_image_input(mode): """Hiển thị hoặc ẩn ô Drop Image dựa trên mode.""" return gr.update(visible=(mode == "img2img")) with gr.Blocks(theme=gr.themes.Soft()) as demo: gr.Markdown( """ # 🌟 **Stable Diffusion Interface** Generate stunning images from text or modify existing images with AI-powered tools. """ ) # Thiết lập giao diện with gr.Row(): with gr.Column(): prompt = gr.Textbox( label="🎨 Prompt", placeholder="Enter your creative idea here...", lines=2 ) mode = gr.Radio( choices=["txt2img", "img2img"], value="txt2img", label="Mode", interactive=True ) init_image = gr.Image( label="Drop Image (for img2img mode)", type="pil", visible=False ) mode.change(toggle_image_input, inputs=mode, outputs=init_image) negative_prompt = gr.Textbox( label="Negative Prompt", placeholder="Anything to avoid in the image", lines=2 ) threads = gr.Slider(-1, 64, value=-1, step=1, label="Threads", interactive=True) weight_type = gr.Dropdown(choices=["f32", "f16", "q4_0", "q4_1", "q5_0", "q5_1", "q8_0", "q2_k", "q3_k", "q4_k"], value="f32", label="Weight Type") cfg_scale = gr.Slider(0, 20, value=7.0, step=0.1, label="CFG Scale", interactive=True) strength = gr.Slider(0, 1, value=0.75, step=0.01, label="Strength", interactive=True) style_ratio = gr.Slider(0, 1, value=0.2, step=0.01, label="Style Ratio", interactive=True) control_strength = gr.Slider(0, 1, value=0.9, step=0.01, label="Control Strength", interactive=True) sampling_method = gr.Dropdown(choices=["euler", "euler_a", "heun", "dpm2", "dpm++2s_a", "dpm++2m", "dpm++2mv2", "ipndm", "ipndm_v", "lcm"], value="euler_a", label="Sampling Method") batch_count = gr.Slider(1, 10, value=1, step=1, label="Batch Count", interactive=True) schedule = gr.Dropdown(choices=["discrete", "karras", "exponential", "ays", "gits"], value="discrete", label="Denoiser Schedule") clip_skip = gr.Slider(-1, 2, value=-1, step=1, label="Clip Skip", interactive=True) vae_tiling = gr.Checkbox(label="VAE Tiling", interactive=True) vae_on_cpu = gr.Checkbox(label="VAE on CPU", interactive=True) clip_on_cpu = gr.Checkbox(label="CLIP on CPU", interactive=True) control_net_cpu = gr.Checkbox(label="Control Net on CPU", interactive=True) canny = gr.Checkbox(label="Apply Canny Preprocessor", interactive=True) color = gr.Checkbox(label="Color Logs", interactive=True) verbose = gr.Checkbox(label="Verbose Output", interactive=True) rng = gr.Radio(choices=["std_default", "cuda"], value="cuda", label="Random Number Generator", interactive=True) with gr.Column(): height = gr.Slider( 128, 1024, value=512, step=64, label="Image Height (px)", interactive=True ) width = gr.Slider( 128, 1024, value=512, step=64, label="Image Width (px)", interactive=True ) steps = gr.Slider( 1, 100, value=20, step=1, label="Sampling Steps", interactive=True ) seed = gr.Slider( 1, 10000, value=42, step=1, label="Seed", interactive=True ) generate_btn = gr.Button("Run") output_image = gr.Image(label="Generated Image") logs_output = gr.Textbox(label="Logs", interactive=False, lines=15) generate_btn.click( run_command, inputs=[ prompt, mode, height, width, steps, seed, init_image, threads, weight_type, negative_prompt, cfg_scale, strength, style_ratio, control_strength, sampling_method, batch_count, schedule, clip_skip, vae_tiling, vae_on_cpu, clip_on_cpu, control_net_cpu, canny, color, verbose, rng ], outputs=[output_image, logs_output], ) demo.launch()