app.py

import gradio as gr
import numpy as np
import random
import torch
import spaces

from PIL import Image
from diffusers import FlowMatchEulerDiscreteScheduler
from optimization import optimize_pipeline_
from qwenimage.pipeline_qwenimage_edit_plus import QwenImageEditPlusPipeline
from qwenimage.transformer_qwenimage import QwenImageTransformer2DModel
from qwenimage.qwen_fa3_processor import QwenDoubleStreamAttnProcessorFA3

import math
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file

from PIL import Image
import os
import gradio as gr
from gradio_client import Client, handle_file
import tempfile
from huggingface_hub import InferenceClient


# --- Model Loading ---
dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"

pipe = QwenImageEditPlusPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509", torch_dtype=dtype).to(device)

# Load the relight LoRA
pipe.load_lora_weights(
        "dx8152/Qwen-Image-Edit-2509-Relight", 
        weight_name="Qwen-Edit-Relight.safetensors", adapter_name="relight"
    )

pipe.load_lora_weights("lightx2v/Qwen-Image-Lightning",
        weight_name="Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors", adapter_name="lightning")
pipe.set_adapters(["relight", "lightning"], adapter_weights=[1., 1.])
pipe.fuse_lora(adapter_names=["relight", "lightning"], lora_scale=1)
pipe.unload_lora_weights()

pipe.transformer.__class__ = QwenImageTransformer2DModel
pipe.transformer.set_attn_processor(QwenDoubleStreamAttnProcessorFA3())

optimize_pipeline_(pipe, image=[Image.new("RGB", (1024, 1024)), Image.new("RGB", (1024, 1024))], prompt="prompt")


MAX_SEED = np.iinfo(np.int32).max

# Initialize translation client
translation_client = InferenceClient(
    api_key=os.environ.get("HF_TOKEN"),
)

def translate_to_chinese(text: str) -> str:
    """Translate any language text to Chinese using Qwen API."""
    if not text or not text.strip():
        return ""
    
    # Check if text is already primarily Chinese
    chinese_chars = sum(1 for char in text if '\u4e00' <= char <= '\u9fff')
    if chinese_chars / max(len(text), 1) > 0.5:
        # Already mostly Chinese, return as is
        return text
    
    try:
        completion = translation_client.chat.completions.create(
            model="Qwen/Qwen3-Next-80B-A3B-Instruct:novita",
            messages=[
                {
                    "role": "system",
                    "content": "You are a professional translator. Translate the user's text to Chinese. Only output the translated text, nothing else."
                },
                {
                    "role": "user",
                    "content": f"Translate this to Chinese: {text}"
                }
            ],
            max_tokens=500,
        )
        
        translated = completion.choices[0].message.content.strip()
        print(f"Translated '{text}' to '{translated}'")
        return translated
    except Exception as e:
        print(f"Translation error: {e}")
        # Fallback to original text if translation fails
        return text

def _generate_video_segment(input_image_path: str, output_image_path: str, prompt: str, request: gr.Request) -> str:
    """Generates a single video segment using the external service."""
    x_ip_token = request.headers['x-ip-token']
    video_client = Client("multimodalart/wan-2-2-first-last-frame", headers={"x-ip-token": x_ip_token})
    result = video_client.predict(
        start_image_pil=handle_file(input_image_path),
        end_image_pil=handle_file(output_image_path),
        prompt=prompt, api_name="/generate_video",
    )
    return result[0]["video"]

def build_relight_prompt(light_type, light_direction, light_intensity, illumination_env, prompt):
    """Build the relighting prompt based on user selections - Qwen style."""
    
    # Priority 1: User's prompt (translated to Chinese if needed)
    if prompt and prompt.strip():
        translated = translate_to_chinese(prompt)
        # Add trigger word if not already present
        if "重新照明" not in translated:
            return f"重新照明,{translated}"
        return translated
    
    # Priority 2: Build from controls
    prompt_parts = ["重新照明"]
    
    # Light type descriptions (expanded from IC-Light style but in Chinese)
    light_descriptions = {
        "none": "",
        "soft_window": "窗帘透光（柔和漫射）",
        "golden_hour": "金色黄昏的温暖光线",
        "studio": "专业摄影棚的均匀光线",
        "dramatic": "戏剧性的高对比度光线",
        "natural": "自然日光",
        "neon": "霓虹灯光效果",
        "candlelight": "烛光的温暖氛围",
        "moonlight": "月光的冷色调",
        "sunrise": "日出的柔和光线",
        "sunset_sea": "海面日落光线",
        "overcast": "阴天的柔和漫射光",
        "harsh_sun": "强烈的正午阳光",
        "twilight": "黄昏时分的神秘光线",
        "aurora": "极光般的多彩光线",
        "firelight": "篝火的跳动光线",
        "lightning": "闪电的瞬间强光",
        "underwater": "水下的柔和蓝光",
        "foggy": "雾气中的柔和扩散光",
        "magic": "魔法般的神秘光芒",
        "cyberpunk": "赛博朋克风格的RGB霓虹光",
        "warm_home": "家庭温馨的暖色光",
        "cold_industrial": "冷酷的工业照明",
        "spotlight": "聚光灯效果",
        "rim_light": "边缘光效果",
    }
    
    # Direction descriptions (from IC-Light)
    direction_descriptions = {
        "none": "",
        "front": "正面照射",
        "side": "侧面照射",
        "left": "左侧照射",
        "right": "右侧照射",
        "back": "背后照射（逆光）",
        "top": "上方照射",
        "bottom": "下方照射",
        "diagonal": "对角线照射",
    }
    
    # Intensity descriptions
    intensity_descriptions = {
        "none": "",
        "soft": "柔和强度",
        "medium": "中等强度",
        "strong": "强烈强度",
    }
    
    # Illumination environments (from IC-Light vary, translated)
    illumination_envs = {
        "none": "",
        "sunshine_window": "阳光从窗户透入",
        "neon_city": "霓虹夜景，城市灯光",
        "sci_fi_rgb": "科幻RGB发光，赛博朋克风格",
        "warm_bedroom": "温暖氛围，家中，卧室",
        "magic_lit": "魔法照明",
        "gothic_cave": "邪恶哥特风格，洞穴中",
        "light_shadow": "光影交错",
        "window_shadow": "窗户投影",
        "soft_studio": "柔和摄影棚灯光",
        "cozy_bedroom": "家庭氛围，温馨卧室照明",
        "wong_kar_wai": "王家卫风格霓虹灯，温暖色调",
        "moonlight_curtains": "月光透过窗帘",
        "stormy_sky": "暴风雨天空照明",
        "underwater_glow": "水下发光，深海",
        "foggy_forest": "雾中森林黎明",
        "meadow_golden": "草地上的黄金时刻",
        "rainbow_neon": "彩虹反射，霓虹",
        "apocalyptic": "末日烟雾氛围",
        "emergency_red": "红色紧急灯光",
        "mystical_forest": "神秘发光，魔法森林",
        "campfire": "篝火光芒",
        "industrial_harsh": "严酷工业照明",
        "mountain_sunrise": "山中日出",
        "desert_evening": "沙漠黄昏",
        "dark_alley": "黑暗小巷的月光",
        "fairground": "游乐场的金色光芒",
        "forest_midnight": "森林深夜",
        "twilight_purple": "黄昏的紫粉色调",
        "foggy_morning": "雾蒙蒙的早晨",
        "rustic_candle": "乡村风格烛光",
        "office_fluorescent": "办公室荧光灯",
        "storm_lightning": "暴风雨中的闪电",
        "fireplace_night": "夜晚壁炉的温暖光芒",
        "ethereal_magic": "空灵发光，魔法森林",
        "beach_dusky": "海滩的黄昏",
        "trees_afternoon": "树林中的午后光线",
        "urban_blue_neon": "蓝色霓虹灯，城市街道",
        "rain_police": "雨中红蓝警灯",
        "aurora_arctic": "极光，北极景观",
        "foggy_mountains": "雾中山峦日出",
        "city_skyline": "城市天际线的黄金时刻",
        "twilight_mist": "神秘黄昏，浓雾",
        "forest_rays": "森林空地的清晨光线",
        "festival_lantern": "节日多彩灯笼光",
        "stained_glass": "彩色玻璃的柔和光芒",
        "dark_spotlight": "黑暗房间的强烈聚光",
        "lake_evening": "湖面柔和的黄昏光",
        "cave_crystal": "洞穴水晶反射",
        "autumn_forest": "秋林中的鲜艳光线",
        "snowfall_dusk": "黄昏轻柔降雪",
        "winter_hazy": "冬日清晨的朦胧光",
        "rain_city": "雨中城市灯光倒影",
        "trees_golden_sun": "金色阳光穿过树林",
        "fireflies_summer": "萤火虫点亮夏夜",
        "forge_embers": "锻造炉的发光余烬",
        "gothic_castle": "哥特城堡的昏暗烛光",
        "starlight_midnight": "午夜明亮星光",
        "rural_sunset": "乡村的温暖日落",
        "haunted_flicker": "闹鬼房屋的闪烁灯光",
        "desert_mirage": "沙漠日落海市蜃楼般的光",
        "storm_beams": "风暴云中穿透的金色光束",
    }
    
    # Build the prompt - Qwen style (comma-separated, Chinese)
    if light_type != "none":
        prompt_parts.append(light_descriptions.get(light_type, ""))
    
    if illumination_env != "none":
        prompt_parts.append(illumination_envs.get(illumination_env, ""))
    
    if light_direction != "none":
        prompt_parts.append(direction_descriptions.get(light_direction, ""))
    
    if light_intensity != "none":
        prompt_parts.append(intensity_descriptions.get(light_intensity, ""))
    
    final_prompt = ",".join([p for p in prompt_parts if p])
    
    # Add instruction if we have settings
    if len(prompt_parts) > 1:
        final_prompt += ",对图片进行重新照明"
    
    return final_prompt if len(prompt_parts) > 1 else "重新照明,使用自然光线对图片进行重新照明"


@spaces.GPU
def infer_relight(
    image,
    light_type,
    light_direction,
    light_intensity,
    illumination_env,
    prompt,
    seed,
    randomize_seed,
    true_guidance_scale,
    num_inference_steps,
    height,
    width,
    prev_output = None,
    progress=gr.Progress(track_tqdm=True)
):
    final_prompt = build_relight_prompt(light_type, light_direction, light_intensity, illumination_env, prompt)
    print(f"Generated Prompt: {final_prompt}")

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    generator = torch.Generator(device=device).manual_seed(seed)

    # Choose input image (prefer uploaded, else last output)
    pil_images = []
    if image is not None:
        if isinstance(image, Image.Image):
            pil_images.append(image.convert("RGB"))
        elif hasattr(image, "name"):
            pil_images.append(Image.open(image.name).convert("RGB"))
    elif prev_output:
        pil_images.append(prev_output.convert("RGB"))

    if len(pil_images) == 0:
        raise gr.Error("Please upload an image first.")

    result = pipe(
        image=pil_images,
        prompt=final_prompt,
        height=height if height != 0 else None,
        width=width if width != 0 else None,
        num_inference_steps=num_inference_steps,
        generator=generator,
        true_cfg_scale=true_guidance_scale,
        num_images_per_prompt=1,
    ).images[0]

    return result, seed, final_prompt

def create_video_between_images(input_image, output_image, prompt: str, request: gr.Request) -> str:
    """Create a video between the input and output images."""
    if input_image is None or output_image is None:
        raise gr.Error("Both input and output images are required to create a video.")
    
    try:
        
        with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as tmp:
            input_image.save(tmp.name)
            input_image_path = tmp.name
        
        output_pil = Image.fromarray(output_image.astype('uint8'))
        with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as tmp:
            output_pil.save(tmp.name)
            output_image_path = tmp.name
            
        video_path = _generate_video_segment(
            input_image_path, 
            output_image_path, 
            prompt if prompt else "Relighting transformation",
            request
        )
        return video_path
    except Exception as e:
        raise gr.Error(f"Video generation failed: {e}")


# --- UI ---
css = '''
#col-container { max-width: 1200px; margin: 0 auto; }
.dark .progress-text{color: white !important}
#examples{max-width: 1200px; margin: 0 auto; }
.radio-group {display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 8px;}
.radio-group [data-testid="block-info"] { display: none !important }
'''

def reset_all():
    return ["none", "none", "none", "none", "", False, True]

def end_reset():
    return False

def update_dimensions_on_upload(image):
    if image is None:
        return 1024, 1024
    
    original_width, original_height = image.size
    
    if original_width > original_height:
        new_width = 1024
        aspect_ratio = original_height / original_width
        new_height = int(new_width * aspect_ratio)
    else:
        new_height = 1024
        aspect_ratio = original_width / original_height
        new_width = int(new_height * aspect_ratio)
        
    # Ensure dimensions are multiples of 8
    new_width = (new_width // 8) * 8
    new_height = (new_height // 8) * 8
    
    return new_width, new_height


with gr.Blocks(theme=gr.themes.Citrus(), css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown("## 💡 Qwen Image Edit — Relighting Control")
        gr.Markdown("""
            Qwen Image Edit 2509 for Image Relighting ✨ 
            Using [dx8152's Qwen-Image-Edit-2509-Relight LoRA](https://huggingface.co/dx8152/Qwen-Image-Edit-2509-Relight) and [lightx2v/Qwen-Image-Lightning](https://huggingface.co/lightx2v/Qwen-Image-Lightning) for 4-step inference 💨
            """
        )
        with gr.Row():
            with gr.Column(scale=1):
                image = gr.Image(label="Input Image", type="pil")
                prev_output = gr.Image(value=None, visible=False)
                is_reset = gr.Checkbox(value=False, visible=False)

                with gr.Accordion("💡 Light Type", open=True):
                    light_type = gr.Radio(
                        choices=[
                            ("None", "none"),
                            ("Soft Window Light", "soft_window"),
                            ("Golden Hour", "golden_hour"),
                            ("Studio Lighting", "studio"),
                            ("Dramatic", "dramatic"),
                            ("Natural Daylight", "natural"),
                            ("Neon", "neon"),
                            ("Candlelight", "candlelight"),
                            ("Moonlight", "moonlight"),
                            ("Sunrise", "sunrise"),
                            ("Sunset over Sea", "sunset_sea"),
                            ("Overcast", "overcast"),
                            ("Harsh Sunlight", "harsh_sun"),
                            ("Twilight", "twilight"),
                            ("Aurora", "aurora"),
                            ("Firelight", "firelight"),
                            ("Lightning", "lightning"),
                            ("Underwater", "underwater"),
                            ("Foggy", "foggy"),
                            ("Magic Light", "magic"),
                            ("Cyberpunk", "cyberpunk"),
                            ("Warm Home", "warm_home"),
                            ("Cold Industrial", "cold_industrial"),
                            ("Spotlight", "spotlight"),
                            ("Rim Light", "rim_light"),
                        ],
                        value="none",
                        elem_classes="radio-group"
                    )
                
                with gr.Accordion("🧭 Light Direction", open=True):
                    light_direction = gr.Radio(
                        choices=[
                            ("None", "none"),
                            ("Front", "front"),
                            ("Side", "side"),
                            ("Left", "left"),
                            ("Right", "right"),
                            ("Back (Backlight)", "back"),
                            ("Top", "top"),
                            ("Bottom", "bottom"),
                            ("Diagonal", "diagonal"),
                        ],
                        value="none",
                        elem_classes="radio-group"
                    )
                
                with gr.Accordion("⚡ Light Intensity", open=True):
                    light_intensity = gr.Radio(
                        choices=[
                            ("None", "none"),
                            ("Soft", "soft"),
                            ("Medium", "medium"),
                            ("Strong", "strong"),
                        ],
                        value="none",
                        elem_classes="radio-group"
                    )
                
                with gr.Accordion("🌍 Illumination Environment", open=False):
                    illumination_env = gr.Radio(
                        choices=[
                            ("None", "none"),
                            ("Sunshine from Window", "sunshine_window"),
                            ("Neon Night, City", "neon_city"),
                            ("Sci-Fi RGB Glowing, Cyberpunk", "sci_fi_rgb"),
                            ("Warm Atmosphere, at Home, Bedroom", "warm_bedroom"),
                            ("Magic Lit", "magic_lit"),
                            ("Evil, Gothic, in a Cave", "gothic_cave"),
                            ("Light and Shadow", "light_shadow"),
                            ("Shadow from Window", "window_shadow"),
                            ("Soft Studio Lighting", "soft_studio"),
                            ("Home Atmosphere, Cozy Bedroom", "cozy_bedroom"),
                            ("Neon, Wong Kar-wai, Warm", "wong_kar_wai"),
                            ("Moonlight through Curtains", "moonlight_curtains"),
                            ("Stormy Sky Lighting", "stormy_sky"),
                            ("Underwater Glow, Deep Sea", "underwater_glow"),
                            ("Foggy Forest at Dawn", "foggy_forest"),
                            ("Golden Hour in a Meadow", "meadow_golden"),
                            ("Rainbow Reflections, Neon", "rainbow_neon"),
                            ("Apocalyptic, Smoky Atmosphere", "apocalyptic"),
                            ("Red Glow, Emergency Lights", "emergency_red"),
                            ("Mystical Glow, Enchanted Forest", "mystical_forest"),
                            ("Campfire Light", "campfire"),
                            ("Harsh, Industrial Lighting", "industrial_harsh"),
                            ("Sunrise in the Mountains", "mountain_sunrise"),
                            ("Evening Glow in the Desert", "desert_evening"),
                            ("Moonlight in a Dark Alley", "dark_alley"),
                            ("Golden Glow at a Fairground", "fairground"),
                            ("Midnight in the Forest", "forest_midnight"),
                            ("Purple and Pink Hues at Twilight", "twilight_purple"),
                            ("Foggy Morning, Muted Light", "foggy_morning"),
                            ("Candle-lit Room, Rustic Vibe", "rustic_candle"),
                            ("Fluorescent Office Lighting", "office_fluorescent"),
                            ("Lightning Flash in Storm", "storm_lightning"),
                            ("Night, Cozy Warm Light from Fireplace", "fireplace_night"),
                            ("Ethereal Glow, Magical Forest", "ethereal_magic"),
                            ("Dusky Evening on a Beach", "beach_dusky"),
                            ("Afternoon Light Filtering through Trees", "trees_afternoon"),
                            ("Blue Neon Light, Urban Street", "urban_blue_neon"),
                            ("Red and Blue Police Lights in Rain", "rain_police"),
                            ("Aurora Borealis Glow, Arctic Landscape", "aurora_arctic"),
                            ("Sunrise through Foggy Mountains", "foggy_mountains"),
                            ("Golden Hour on a City Skyline", "city_skyline"),
                            ("Mysterious Twilight, Heavy Mist", "twilight_mist"),
                            ("Early Morning Rays, Forest Clearing", "forest_rays"),
                            ("Colorful Lantern Light at Festival", "festival_lantern"),
                            ("Soft Glow through Stained Glass", "stained_glass"),
                            ("Harsh Spotlight in Dark Room", "dark_spotlight"),
                            ("Mellow Evening Glow on a Lake", "lake_evening"),
                            ("Crystal Reflections in a Cave", "cave_crystal"),
                            ("Vibrant Autumn Lighting in a Forest", "autumn_forest"),
                            ("Gentle Snowfall at Dusk", "snowfall_dusk"),
                            ("Hazy Light of a Winter Morning", "winter_hazy"),
                            ("Rain-soaked Reflections in City Lights", "rain_city"),
                            ("Golden Sunlight Streaming through Trees", "trees_golden_sun"),
                            ("Fireflies Lighting up a Summer Night", "fireflies_summer"),
                            ("Glowing Embers from a Forge", "forge_embers"),
                            ("Dim Candlelight in a Gothic Castle", "gothic_castle"),
                            ("Midnight Sky with Bright Starlight", "starlight_midnight"),
                            ("Warm Sunset in a Rural Village", "rural_sunset"),
                            ("Flickering Light in a Haunted House", "haunted_flicker"),
                            ("Desert Sunset with Mirage-like Glow", "desert_mirage"),
                            ("Golden Beams Piercing through Storm Clouds", "storm_beams"),
                        ],
                        value="none",
                        elem_classes="radio-group"
                    )
                
                with gr.Accordion("✍️ Custom Prompt", open=False):
                    prompt = gr.Textbox(
                        placeholder="Example: Add warm sunset lighting from the right",
                        lines=3
                    )
                
                with gr.Row():
                    reset_btn = gr.Button("🔄 Reset")
                    run_btn = gr.Button("✨ Generate", 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)
                    true_guidance_scale = gr.Slider(label="True Guidance Scale", minimum=1.0, maximum=10.0, step=0.1, value=1.0)
                    num_inference_steps = gr.Slider(label="Inference Steps", minimum=1, maximum=40, step=1, value=4)
                    height = gr.Slider(label="Height", minimum=256, maximum=2048, step=8, value=1024)
                    width = gr.Slider(label="Width", minimum=256, maximum=2048, step=8, value=1024)

            with gr.Column(scale=1):
                result = gr.Image(label="Output Image", interactive=False)
                prompt_preview = gr.Textbox(label="Processed Prompt", interactive=False)
                create_video_button = gr.Button("🎥 Create Video Between Images", variant="secondary", visible=False)
                with gr.Group(visible=False) as video_group:
                    video_output = gr.Video(label="Generated Video", show_download_button=True, autoplay=True)
                    
    inputs = [
        image, light_type, light_direction, light_intensity, illumination_env, prompt,
        seed, randomize_seed, true_guidance_scale, num_inference_steps, height, width, prev_output
    ]
    outputs = [result, seed, prompt_preview]

    # Reset behavior
    reset_btn.click(
        fn=reset_all,
        inputs=None,
        outputs=[light_type, light_direction, light_intensity, illumination_env, prompt, is_reset],
        queue=False
    ).then(fn=end_reset, inputs=None, outputs=[is_reset], queue=False)

    # Manual generation with video button visibility control
    def infer_and_show_video_button(*args):
        result_img, result_seed, result_prompt = infer_relight(*args)
        # Show video button if we have both input and output images
        show_button = args[0] is not None and result_img is not None
        return result_img, result_seed, result_prompt, gr.update(visible=show_button)
    
    run_event = run_btn.click(
        fn=infer_and_show_video_button, 
        inputs=inputs, 
        outputs=outputs + [create_video_button]
    )

    # Video creation
    create_video_button.click(
        fn=lambda: gr.update(visible=True), 
        outputs=[video_group],
        api_name=False
    ).then(
        fn=create_video_between_images,
        inputs=[image, result, prompt_preview],
        outputs=[video_output],
        api_name=False
    )

    # Examples
    gr.Examples(
        examples=[
            ["harold.png", "dramatic", "side", "soft", "none", "", 0, True, 1.0, 4, 672, 1024],
            ["distracted.png", "golden_hour", "side", "strong", "none", "", 0, True, 1.0, 4, 640, 1024],
            ["disaster.jpg", "moonlight", "front", "medium", "neon_city", "", 0, True, 1.0, 4, 640, 1024],
        ],
        inputs=[image, light_type, light_direction, light_intensity, illumination_env, prompt,
                seed, randomize_seed, true_guidance_scale, num_inference_steps, height, width],
        outputs=outputs,
        fn=infer_relight,
        cache_examples="lazy",
        elem_id="examples"
    )
    
    # Image upload triggers dimension update and control reset
    image.upload(
        fn=update_dimensions_on_upload,
        inputs=[image],
        outputs=[width, height]
    ).then(
        fn=reset_all,
        inputs=None,
        outputs=[light_type, light_direction, light_intensity, illumination_env, prompt, is_reset],
        queue=False
    ).then(
        fn=end_reset, 
        inputs=None, 
        outputs=[is_reset], 
        queue=False
    )


    # Live updates
    def maybe_infer(is_reset, progress=gr.Progress(track_tqdm=True), *args):
        if is_reset:
            return gr.update(), gr.update(), gr.update(), gr.update()
        else:
            result_img, result_seed, result_prompt = infer_relight(*args)
            # Show video button if we have both input and output
            show_button = args[0] is not None and result_img is not None
            return result_img, result_seed, result_prompt, gr.update(visible=show_button)

    control_inputs = [
        image, light_type, light_direction, light_intensity, illumination_env, prompt,
        seed, randomize_seed, true_guidance_scale, num_inference_steps, height, width, prev_output
    ]
    control_inputs_with_flag = [is_reset] + control_inputs

    for control in [light_type, light_direction, light_intensity, illumination_env]:
        control.input(fn=maybe_infer, inputs=control_inputs_with_flag, outputs=outputs + [create_video_button])
    
    run_event.then(lambda img, *_: img, inputs=[result], outputs=[prev_output])

demo.launch()