Delete app.py

app.py

@@ -1,304 +0,0 @@
-import gradio as gr
-import numpy as np
-import random
-import torch
-import spaces
-import math
-import os
-from PIL import Image
-from diffusers import QwenImagePipeline, FlowMatchEulerDiscreteScheduler
-from qwenimage.qwen_fa3_processor import QwenDoubleStreamAttnProcessorFA3
-from optimization import optimize_pipeline_
-from gradio.themes import Soft
-from gradio.themes.utils import colors, fonts, sizes
-from typing import Iterable
-
-from huggingface_hub import login
-
-# Optional: Login if you have set the HF token in environment variables
-if os.environ.get('hf'):
-    login(token=os.environ.get('hf'))
-
-# -----------------------------------------------------------------------------
-# Theme Configuration
-# -----------------------------------------------------------------------------
-
-colors.orange_red = colors.Color(
-    name="orange_red",
-    c50="#FFF0E5",
-    c100="#FFE0CC",
-    c200="#FFC299",
-    c300="#FFA366",
-    c400="#FF8533",
-    c500="#FF4500",
-    c600="#E63E00",
-    c700="#CC3700",
-    c800="#B33000",
-    c900="#992900",
-    c950="#802200",
-)
-
-class OrangeRedTheme(Soft):
-    def __init__(
-        self,
-        *,
-        primary_hue: colors.Color | str = colors.gray,
-        secondary_hue: colors.Color | str = colors.orange_red,
-        neutral_hue: colors.Color | str = colors.slate,
-        text_size: sizes.Size | str = sizes.text_lg,
-        font: fonts.Font | str | Iterable[fonts.Font | str] = (
-            fonts.GoogleFont("Outfit"), "Arial", "sans-serif",
-        ),
-        font_mono: fonts.Font | str | Iterable[fonts.Font | str] = (
-            fonts.GoogleFont("IBM Plex Mono"), "ui-monospace", "monospace",
-        ),
-    ):
-        super().__init__(
-            primary_hue=primary_hue,
-            secondary_hue=secondary_hue,
-            neutral_hue=neutral_hue,
-            text_size=text_size,
-            font=font,
-            font_mono=font_mono,
-        )
-        super().set(
-            background_fill_primary="*primary_50",
-            background_fill_primary_dark="*primary_900",
-            body_background_fill="linear-gradient(135deg, *primary_200, *primary_100)",
-            body_background_fill_dark="linear-gradient(135deg, *primary_900, *primary_800)",
-            button_primary_text_color="white",
-            button_primary_text_color_hover="white",
-            button_primary_background_fill="linear-gradient(90deg, *secondary_500, *secondary_600)",
-            button_primary_background_fill_hover="linear-gradient(90deg, *secondary_600, *secondary_700)",
-            button_primary_background_fill_dark="linear-gradient(90deg, *secondary_600, *secondary_700)",
-            button_primary_background_fill_hover_dark="linear-gradient(90deg, *secondary_500, *secondary_600)",
-            button_secondary_text_color="black",
-            button_secondary_text_color_hover="white",
-            button_secondary_background_fill="linear-gradient(90deg, *primary_300, *primary_300)",
-            button_secondary_background_fill_hover="linear-gradient(90deg, *primary_400, *primary_400)",
-            button_secondary_background_fill_dark="linear-gradient(90deg, *primary_500, *primary_600)",
-            button_secondary_background_fill_hover_dark="linear-gradient(90deg, *primary_500, *primary_500)",
-            slider_color="*secondary_500",
-            slider_color_dark="*secondary_600",
-            block_title_text_weight="600",
-            block_border_width="3px",
-            block_shadow="*shadow_drop_lg",
-            button_primary_shadow="*shadow_drop_lg",
-            button_large_padding="11px",
-            color_accent_soft="*primary_100",
-            block_label_background_fill="*primary_200",
-        )
-
-orange_red_theme = OrangeRedTheme()
-
-# -----------------------------------------------------------------------------
-# Model & Scheduler Setup
-# -----------------------------------------------------------------------------
-
-dtype = torch.bfloat16
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-scheduler_config = {
-    "base_image_seq_len": 256,
-    "base_shift": math.log(3),  # We use shift=3 in distillation
-    "invert_sigmas": False,
-    "max_image_seq_len": 8192,
-    "max_shift": math.log(3),  # We use shift=3 in distillation
-    "num_train_timesteps": 1000,
-    "shift": 1.0,
-    "shift_terminal": None,
-    "stochastic_sampling": False,
-    "time_shift_type": "exponential",
-    "use_beta_sigmas": False,
-    "use_dynamic_shifting": True,
-    "use_exponential_sigmas": False,
-    "use_karras_sigmas": False,
-}
-scheduler = FlowMatchEulerDiscreteScheduler.from_config(scheduler_config)
-
-# Load the model pipeline
-pipe = QwenImagePipeline.from_pretrained(
-    "Qwen/Qwen-Image-2512", 
-    torch_dtype=dtype
-).to(device)
-
-# Load Lightning LoRA
-pipe.load_lora_weights(
-    "Wuli-art/Qwen-Image-2512-Turbo-LoRA", 
-    weight_name="Wuli-Qwen-Image-2512-Turbo-LoRA-4steps-V1.0-bf16.safetensors"
-)
-pipe.fuse_lora()
-
-# Enable Flash Attention 3 if available
-try:
-    pipe.transformer.set_attn_processor(QwenDoubleStreamAttnProcessorFA3())
-except Exception as e:
-    print(f"Warning: Could not set FA3 processor: {e}")
-
-# --- Ahead-of-time compilation ---
-try:
-    optimize_pipeline_(pipe, prompt="prompt")
-except Exception as e:
-    print(f"Warning: Optimization failed: {e}")
-
-# -----------------------------------------------------------------------------
-# Inference Logic
-# -----------------------------------------------------------------------------
-
-MAX_SEED = np.iinfo(np.int32).max
-
-def get_image_size(aspect_ratio):
-    """Converts aspect ratio string to width, height tuple."""
-    if aspect_ratio == "1:1":
-        return 1328, 1328
-    elif aspect_ratio == "16:9":
-        return 1664, 928
-    elif aspect_ratio == "9:16":
-        return 928, 1664
-    elif aspect_ratio == "4:3":
-        return 1472, 1104
-    elif aspect_ratio == "3:4":
-        return 1104, 1472
-    elif aspect_ratio == "3:2":
-        return 1584, 1056
-    elif aspect_ratio == "2:3":
-        return 1056, 1584
-    else:
-        return 1328, 1328
-
-@spaces.GPU(duration=120)
-def infer(
-    prompt,
-    seed=42,
-    randomize_seed=False,
-    aspect_ratio="16:9",
-    guidance_scale=1.0,
-    num_inference_steps=4,
-    progress=gr.Progress(track_tqdm=True),
-):
-    """
-    Generates an image using the local Qwen-Image diffusers pipeline.
-    """
-    # Hardcode the negative prompt
-    negative_prompt = "低分辨率，低画质，肢体畸形，手指畸形，画面过饱和，蜡像感，人脸无细节，过度光滑，画面具有AI感。构图混乱。文字模糊，扭曲。"
-    
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    # Convert aspect ratio to width and height
-    width, height = get_image_size(aspect_ratio)
-    
-    generator = torch.Generator(device=device).manual_seed(seed)
-    
-    print(f"Generating with Prompt: '{prompt}'")
-    print(f"Size: {width}x{height}, Steps: {num_inference_steps}, Guidance: {guidance_scale}")
-
-    # Generate the image
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        width=width,
-        height=height,
-        num_inference_steps=num_inference_steps,
-        generator=generator,
-        true_cfg_scale=guidance_scale,
-        guidance_scale=1.0  # Use a fixed default for distilled guidance
-    ).images[0]
-
-    return image, seed
-
-# -----------------------------------------------------------------------------
-# UI Layout
-# -----------------------------------------------------------------------------
-
-examples = [
-        '一位身着淡雅水粉色交领襦裙的年轻女子背对镜头而坐，俯身专注地手持毛笔在素白宣纸上书写"通義千問"四个遒劲汉字。古色古香的室内陈设典雅考究，案头错落摆放着青瓷茶盏与鎏金香炉，一缕熏香轻盈升腾；柔和光线洒落肩头，勾勒出她衣裙的柔美质感与专注神情，仿佛凝固了一段宁静温润的旧时光。',
-        "Realistic still life photography style: A single, fresh apple resting on a clean, soft-textured surface. The apple is slightly off-center, softly backlit to highlight its natural gloss and subtle color gradients—deep crimson red blending into light golden hues. Fine details such as small blemishes, dew drops, and a few light highlights enhance its lifelike appearance. A shallow depth of field gently blurs the neutral background, drawing full attention to the apple. Hyper-detailed 8K resolution, studio lighting, photorealistic render, emphasizing texture and form.",
-        "一位东亚女性，约20-30岁，身材娇小，皮肤白皙如瓷，呈现冷白皮质感，水润光滑，面部轮廓柔和，眼神清澈灵动，眼妆自然清透，睫毛纤长卷翘，唇色为浅粉色，微微上扬的嘴角带着俏皮可爱的笑意。她拥有一头深黑色长发，发丝蓬松柔顺，自然垂落肩头，碎发轻拂脸颊，增添灵动感，发尾微卷，随性散落。身着浅色高质感休闲连衣裙，材质似丝绸或雪纺，搭配一顶贝雷帽，帽檐微微压低，凸显偶像气质。手腕佩戴多条精致手链，金属与珍珠元素交织，正自然展示于镜头前。背景为少女心爆棚的饰品店，店内装修精致，陈列琳琅满目，暖光灯与柔和自然光交织，角落一棵圣诞树点缀着彩灯与装饰物，整体氛围温馨浪漫，画面呈日常快照风格，构图随意却充满生活美感，8K高清摄影。",
-        '一位东亚女性，约20岁，身着白色高定蕾丝连衣裙，裙摆轻盈飘动，露出修长双腿与黑色细跟高跟鞋，发色乌黑，长发自然披肩，肌肤白皙如凝脂，唇色为水润朱红，眼神温柔含光，略带腼腆地望向镜头。她坐在咖啡馆窗边，右手轻扶杯沿，杯中是一杯带有爱心拉花的深棕色咖啡，桌旁放一本翻开的纸质书与一束淡粉色康乃馨。窗外阳光斜洒，照亮她半边脸庞，营造出温暖柔和的氛围。背景为暖色调木质窗框与浅米色窗帘，左侧贴有"圣诞快乐"字样贴纸，窗外可见一棵装饰精美的圣诞树，枝头挂满彩灯与小饰品，整体画面采用超广角拍摄，无畸变，32K高清摄影，呈现出静谧而浪漫的午后时光。图像中未出现其他文字。',
-        "一位年轻的东亚女性，约20-25岁，开怀大笑，双眼弯如月牙，神情明媚愉悦。她肤色白皙，面部轮廓柔和，妆容清新自然，唇色鲜亮。深棕色大波浪卷发蓬松丰盈，随意披散于肩头。上身穿着明黄色细肩带背心，下搭浅蓝色牛仔短裤，整体穿搭休闲活力。背景是一面色彩斑斓的大型街头涂鸦墙，图案鲜明、笔触奔放，阳光从前方斜照，光线充足明亮，营造出自由、热烈而充满街头艺术气息的氛围。",
-        "一位东亚女性，约19岁，身形纤瘦，高鼻梁，黑色长发自然垂落。她身处温馨的咖啡馆内，木质桌面上摆放着一杯拉花咖啡、一块抹茶蛋糕和几张照片卡片。她身穿质感软糯的彩色条纹针织毛衣，纹理细腻，色彩柔和，凸显温暖氛围。她以手肘轻撑桌面，一手托着脸颊，姿态放松自然，脸上带着清甜微笑，眼神灵动而平静，目光或看向镜头或微微偏移，神情慵懒随性。阳光透过发丝洒在面部，肌肤呈现自然状态，无明显妆感。画面为俯视视角，整体光线柔和但略不均匀，存在轻微过曝与运动模糊，保留写实摄影风格的细微噪点，高光不过度溢出，阴影保留细节，构图随意，如iPhone随手抓拍，呈现出真实、松弛又治愈的少女日常瞬间。",
-        "一只美洲豹潜伏在热带雨林的河岸边，压低健壮的身躯，深黄色皮毛上布满比普通豹子更大更黑的斑点，下颌线条强健有力。它目光专注地锁定水中动静，墨绿色河面清晰倒映出它的轮廓。背景是茂密潮湿的蕨类植物与交错缠绕的藤蔓，整体光线昏暗，氛围紧张而原始。图像中无任何文字、人像或人工标识。",
-        "一头雄性盘羊伫立在崎岖裸露的岩石山坡上，灰褐色皮毛粗硬浓密，身躯魁梧结实，肌肉线条分明。它最引人注目的是那对巨大、厚重且向外螺旋盘旋的角，彰显其野性力量。盘羊眼神警觉，目光锐利地扫视四周环境。背景为陡峭险峻的高山地貌，山体嶙峋，植被稀疏低矮，阳光充沛，整体画面凸显高山荒野的苍劲氛围与盘羊顽强的生命力。",
-        "夜空下，璀璨银河如一条发光的河流横贯天际，无数繁星闪烁其间。下方是广袤无垠的沙漠，几座巨大的沙丘在星光映照下轮廓分明，线条柔和流畅。前景中一棵枯死的胡杨树挺立，枝干伸展成极具张力的剪影。整体画面色调深邃，光影对比鲜明，氛围辽阔、静谧，透出宇宙的浩瀚与苍凉。"
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 1024px;
-}
-"""
-
-with gr.Blocks() as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.HTML("""
-        <div id="logo-title">
-            <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/qwen_image_logo.png" alt="Qwen-Image Logo" width="400" style="display: block; margin: 0 auto;">
-            <h2 style="font-style: italic;color: #5b47d1;margin-top: -33px !important;text-align: center;">Fast, 4-steps with Lightx2v Lightning LoRA</h2>
-        </div>
-        """)
-        gr.Markdown("[Learn more](https://github.com/QwenLM/Qwen-Image) about the Qwen-Image series. Try on [Qwen Chat](https://chat.qwen.ai/), or [download model](https://huggingface.co/Qwen/Qwen-Image) to run locally with ComfyUI or diffusers.")
-        
-        with gr.Row():
-            with gr.Column(scale=1):
-                prompt = gr.Text(
-                    label="Prompt",
-                    show_label=False,
-                    placeholder="Enter your prompt",
-                    container=False,
-                )
-                run_button = gr.Button("Run", variant="primary")
-                
-                with gr.Accordion("Advanced Settings", open=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():
-                        aspect_ratio = gr.Radio(
-                            label="Aspect ratio (width:height)",
-                            choices=["1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3"],
-                            value="16:9",
-                        )
-                    with gr.Row():
-                        guidance_scale = gr.Slider(
-                            label="Guidance scale",
-                            minimum=0.0,
-                            maximum=10.0,
-                            step=0.1,
-                            value=1.0,
-                        )
-                        num_inference_steps = gr.Slider(
-                            label="Number of inference steps",
-                            minimum=1,
-                            maximum=20,
-                            step=1,
-                            value=4,
-                        )
-            
-            with gr.Column(scale=1):
-                result = gr.Image(label="Result", show_label=False, type="pil")
-
-        gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=False)
-
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            seed,
-            randomize_seed,
-            aspect_ratio,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
-
-if __name__ == "__main__":
-    demo.launch(css=css, theme=orange_red_theme, mcp_server=True)