Update app.py

app.py

@@ -5,6 +5,7 @@ import logging
 import os
 from pathlib import Path
 from datetime import datetime
+import re
 
 import torch
 import numpy as np
@@ -15,19 +16,42 @@ from diffusers import AutoModel
 import gradio as gr
 import tempfile
 from huggingface_hub import hf_hub_download
+import traceback
+
+# Patch for scaled_dot_product_attention to fix enable_gqa issue
+import torch.nn.functional as F
+
+original_sdpa = F.scaled_dot_product_attention
+
+def patched_scaled_dot_product_attention(query, key, value, attn_mask=None, dropout_p=0.0, is_causal=False, scale=None, enable_gqa=None):
+   # enable_gqa 파라미터를 무시하고 나머지 파라미터만 전달
+   kwargs = {}
+   if attn_mask is not None:
+       kwargs['attn_mask'] = attn_mask
+   if dropout_p != 0.0:
+       kwargs['dropout_p'] = dropout_p
+   if is_causal:
+       kwargs['is_causal'] = is_causal
+   if scale is not None:
+       kwargs['scale'] = scale
+   
+   return original_sdpa(query, key, value, **kwargs)
+
+# 패치 적용
+F.scaled_dot_product_attention = patched_scaled_dot_product_attention
 
 from src.pipeline_wan_nag import NAGWanPipeline
 from src.transformer_wan_nag import NagWanTransformer3DModel
 
 # MMAudio imports
 try:
-    import mmaudio
+   import mmaudio
 except ImportError:
-    os.system("pip install -e .")
-    import mmaudio
+   os.system("pip install -e .")
+   import mmaudio
 
 from mmaudio.eval_utils import (ModelConfig, all_model_cfg, generate as mmaudio_generate, 
-                                load_video, make_video, setup_eval_logging)
+                               load_video, make_video, setup_eval_logging)
 from mmaudio.model.flow_matching import FlowMatching
 from mmaudio.model.networks import MMAudio, get_my_mmaudio
 from mmaudio.model.sequence_config import SequenceConfig
@@ -51,7 +75,7 @@ MIN_FRAMES_MODEL = 8
 MAX_FRAMES_MODEL = 129
 
 DEFAULT_NAG_NEGATIVE_PROMPT = "Static, motionless, still, ugly, bad quality, worst quality, poorly drawn, low resolution, blurry, lack of details"
-DEFAULT_AUDIO_NEGATIVE_PROMPT = "music"
+DEFAULT_AUDIO_NEGATIVE_PROMPT = "music, speech, voice, singing, narration"
 
 # NAG Model Settings
 MODEL_ID = "Wan-AI/Wan2.1-T2V-14B-Diffusers"
@@ -72,421 +96,500 @@ setup_eval_logging()
 
 # Initialize NAG Video Model
 try:
-    vae = AutoencoderKLWan.from_pretrained(MODEL_ID, subfolder="vae", torch_dtype=torch.float32)
-    wan_path = hf_hub_download(repo_id=SUB_MODEL_ID, filename=SUB_MODEL_FILENAME)
-    transformer = NagWanTransformer3DModel.from_single_file(wan_path, torch_dtype=torch.bfloat16)
-    pipe = NAGWanPipeline.from_pretrained(
-        MODEL_ID, vae=vae, transformer=transformer, torch_dtype=torch.bfloat16
-    )
-    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=5.0)
-    pipe.to("cuda")
-
-    pipe.transformer.__class__.attn_processors = NagWanTransformer3DModel.attn_processors
-    pipe.transformer.__class__.set_attn_processor = NagWanTransformer3DModel.set_attn_processor
-    pipe.transformer.__class__.forward = NagWanTransformer3DModel.forward
-    print("NAG Video Model loaded successfully!")
+   vae = AutoencoderKLWan.from_pretrained(MODEL_ID, subfolder="vae", torch_dtype=torch.float32)
+   wan_path = hf_hub_download(repo_id=SUB_MODEL_ID, filename=SUB_MODEL_FILENAME)
+   transformer = NagWanTransformer3DModel.from_single_file(wan_path, torch_dtype=torch.bfloat16)
+   pipe = NAGWanPipeline.from_pretrained(
+       MODEL_ID, vae=vae, transformer=transformer, torch_dtype=torch.bfloat16
+   )
+   pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=5.0)
+   pipe.to("cuda")
+
+   pipe.transformer.__class__.attn_processors = NagWanTransformer3DModel.attn_processors
+   pipe.transformer.__class__.set_attn_processor = NagWanTransformer3DModel.set_attn_processor
+   pipe.transformer.__class__.forward = NagWanTransformer3DModel.forward
+   print("NAG Video Model loaded successfully!")
 except Exception as e:
-    print(f"Error loading NAG Video Model: {e}")
-    pipe = None
+   print(f"Error loading NAG Video Model: {e}")
+   pipe = None
 
 # Initialize MMAudio Model
 def get_mmaudio_model() -> tuple[MMAudio, FeaturesUtils, SequenceConfig]:
-    seq_cfg = audio_model_config.seq_cfg
-    
-    net: MMAudio = get_my_mmaudio(audio_model_config.model_name).to(device, dtype).eval()
-    net.load_weights(torch.load(audio_model_config.model_path, map_location=device, weights_only=True))
-    log.info(f'Loaded MMAudio weights from {audio_model_config.model_path}')
-    
-    feature_utils = FeaturesUtils(tod_vae_ckpt=audio_model_config.vae_path,
-                                  synchformer_ckpt=audio_model_config.synchformer_ckpt,
-                                  enable_conditions=True,
-                                  mode=audio_model_config.mode,
-                                  bigvgan_vocoder_ckpt=audio_model_config.bigvgan_16k_path,
-                                  need_vae_encoder=False)
-    feature_utils = feature_utils.to(device, dtype).eval()
-    
-    return net, feature_utils, seq_cfg
+   seq_cfg = audio_model_config.seq_cfg
+   
+   net: MMAudio = get_my_mmaudio(audio_model_config.model_name).to(device, dtype).eval()
+   net.load_weights(torch.load(audio_model_config.model_path, map_location=device, weights_only=True))
+   log.info(f'Loaded MMAudio weights from {audio_model_config.model_path}')
+   
+   feature_utils = FeaturesUtils(tod_vae_ckpt=audio_model_config.vae_path,
+                                 synchformer_ckpt=audio_model_config.synchformer_ckpt,
+                                 enable_conditions=True,
+                                 mode=audio_model_config.mode,
+                                 bigvgan_vocoder_ckpt=audio_model_config.bigvgan_16k_path,
+                                 need_vae_encoder=False)
+   feature_utils = feature_utils.to(device, dtype).eval()
+   
+   return net, feature_utils, seq_cfg
 
 try:
-    audio_net, audio_feature_utils, audio_seq_cfg = get_mmaudio_model()
-    print("MMAudio Model loaded successfully!")
+   audio_net, audio_feature_utils, audio_seq_cfg = get_mmaudio_model()
+   print("MMAudio Model loaded successfully!")
 except Exception as e:
-    print(f"Error loading MMAudio Model: {e}")
-    audio_net = None
+   print(f"Error loading MMAudio Model: {e}")
+   audio_net = None
+
+# 비디오 프롬프트를 오디오 프롬프트로 변환하는 함수
+def extract_audio_description(video_prompt):
+   """비디오 프롬프트에서 오디오 관련 설명 추출/변환"""
+   
+   # 키워드 매핑
+   audio_keywords = {
+       'car': 'car engine sound, vehicle noise',
+       'porsche': 'sports car engine roar, exhaust sound',
+       'guitar': 'electric guitar playing, guitar music',
+       'concert': 'crowd cheering, live music, applause',
+       'motorcycle': 'motorcycle engine sound, motor rumble',
+       'highway': 'traffic noise, road ambience',
+       'rain': 'rain sounds, water drops',
+       'wind': 'wind blowing sound',
+       'ocean': 'ocean waves, water sounds',
+       'city': 'urban ambience, city traffic sounds',
+       'singer': 'singing voice, vocals',
+       'crowd': 'crowd noise, people talking',
+       'flames': 'fire crackling sound',
+       'pyro': 'fire whoosh, flame burst sound',
+       'explosion': 'explosion sound, blast',
+       'countryside': 'nature ambience, birds chirping',
+       'wheat fields': 'wind through grass, rural ambience',
+       'engine': 'motor sound, mechanical noise',
+       'flat-six engine': 'sports car engine sound',
+       'roaring': 'loud engine roar',
+       'thunderous': 'loud booming sound',
+       'child': 'children playing sounds',
+       'running': 'footsteps sound',
+       'woman': 'ambient sounds',
+       'phone': 'subtle electronic ambience',
+       'advertisement': 'modern ambient sounds'
+   }
+   
+   # 간단한 키워드 기반 변환
+   audio_descriptions = []
+   lower_prompt = video_prompt.lower()
+   
+   for key, value in audio_keywords.items():
+       if key in lower_prompt:
+           audio_descriptions.append(value)
+   
+   # 기본값 설정
+   if not audio_descriptions:
+       # 프롬프트에 명시적인 오디오 설명이 있는지 확인
+       if 'sound' in lower_prompt or 'audio' in lower_prompt or 'noise' in lower_prompt:
+           # 프롬프트에서 오디오 관련 부분만 추출
+           audio_pattern = r'([^.]*(?:sound|audio|noise|music|voice|roar|rumble)[^.]*)'
+           matches = re.findall(audio_pattern, lower_prompt, re.IGNORECASE)
+           if matches:
+               return ', '.join(matches)
+       
+       # 기본 ambient sound
+       return "ambient environmental sounds matching the scene"
+   
+   return ', '.join(audio_descriptions)
 
 # Audio generation function
 @torch.inference_mode()
-def add_audio_to_video(video_path, prompt, audio_negative_prompt, audio_steps, audio_cfg_strength, duration):
-    """Generate and add audio to video using MMAudio"""
-    if audio_net is None:
-        print("MMAudio model not loaded, returning video without audio")
-        return video_path
-        
-    try:
-        rng = torch.Generator(device=device)
-        rng.seed()  # Random seed for audio
-        fm = FlowMatching(min_sigma=0, inference_mode='euler', num_steps=audio_steps)
-        
-        video_info = load_video(video_path, duration)
-        clip_frames = video_info.clip_frames
-        sync_frames = video_info.sync_frames
-        duration = video_info.duration_sec
-        clip_frames = clip_frames.unsqueeze(0)
-        sync_frames = sync_frames.unsqueeze(0)
-        audio_seq_cfg.duration = duration
-        audio_net.update_seq_lengths(audio_seq_cfg.latent_seq_len, audio_seq_cfg.clip_seq_len, audio_seq_cfg.sync_seq_len)
-        
-        audios = mmaudio_generate(clip_frames,
-                                  sync_frames, [prompt],
-                                  negative_text=[audio_negative_prompt],
-                                  feature_utils=audio_feature_utils,
-                                  net=audio_net,
-                                  fm=fm,
-                                  rng=rng,
-                                  cfg_strength=audio_cfg_strength)
-        audio = audios.float().cpu()[0]
-        
-        # Create video with audio
-        video_with_audio_path = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4').name
-        make_video(video_info, video_with_audio_path, audio, sampling_rate=audio_seq_cfg.sampling_rate)
-        
-        return video_with_audio_path
-    except Exception as e:
-        print(f"Error in audio generation: {e}")
-        return video_path
+def add_audio_to_video(video_path, prompt, audio_custom_prompt, audio_negative_prompt, audio_steps, audio_cfg_strength, duration):
+   """Generate and add audio to video using MMAudio"""
+   if audio_net is None:
+       print("MMAudio model not loaded, returning video without audio")
+       return video_path
+       
+   try:
+       # 커스텀 오디오 프롬프트가 있으면 사용, 없으면 비디오 프롬프트에서 추출
+       if audio_custom_prompt and audio_custom_prompt.strip():
+           audio_prompt = audio_custom_prompt.strip()
+       else:
+           audio_prompt = extract_audio_description(prompt)
+       
+       print(f"Original prompt: {prompt}")
+       print(f"Audio prompt: {audio_prompt}")
+       
+       rng = torch.Generator(device=device)
+       rng.manual_seed(random.randint(0, 2**32 - 1))  # 더 명확한 랜덤 시드
+       fm = FlowMatching(min_sigma=0, inference_mode='euler', num_steps=audio_steps)
+       
+       video_info = load_video(video_path, duration)
+       clip_frames = video_info.clip_frames
+       sync_frames = video_info.sync_frames
+       duration = video_info.duration_sec
+       clip_frames = clip_frames.unsqueeze(0)
+       sync_frames = sync_frames.unsqueeze(0)
+       audio_seq_cfg.duration = duration
+       audio_net.update_seq_lengths(audio_seq_cfg.latent_seq_len, audio_seq_cfg.clip_seq_len, audio_seq_cfg.sync_seq_len)
+       
+       # 향상된 네거티브 프롬프트
+       enhanced_negative = f"{audio_negative_prompt}, distortion, static noise, silence, random beeps"
+       
+       audios = mmaudio_generate(clip_frames,
+                                 sync_frames, [audio_prompt],  # 변환된 오디오 프롬프트 사용
+                                 negative_text=[enhanced_negative],
+                                 feature_utils=audio_feature_utils,
+                                 net=audio_net,
+                                 fm=fm,
+                                 rng=rng,
+                                 cfg_strength=audio_cfg_strength)
+       audio = audios.float().cpu()[0]
+       
+       # Create video with audio
+       video_with_audio_path = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4').name
+       make_video(video_info, video_with_audio_path, audio, sampling_rate=audio_seq_cfg.sampling_rate)
+       
+       return video_with_audio_path
+   except Exception as e:
+       print(f"Error in audio generation: {e}")
+       traceback.print_exc()
+       return video_path
 
 # Combined generation function
 def get_duration(prompt, nag_negative_prompt, nag_scale, height, width, duration_seconds, 
-                 steps, seed, randomize_seed, enable_audio, audio_negative_prompt, 
-                 audio_steps, audio_cfg_strength):
-    # Calculate total duration including audio processing if enabled
-    video_duration = int(duration_seconds) * int(steps) * 2.25 + 5
-    audio_duration = 30 if enable_audio else 0  # Additional time for audio processing
-    return video_duration + audio_duration
+                steps, seed, randomize_seed, enable_audio, audio_custom_prompt,
+                audio_negative_prompt, audio_steps, audio_cfg_strength):
+   # Calculate total duration including audio processing if enabled
+   video_duration = int(duration_seconds) * int(steps) * 2.25 + 5
+   audio_duration = 30 if enable_audio else 0  # Additional time for audio processing
+   return video_duration + audio_duration
 
 @spaces.GPU(duration=get_duration)
 def generate_video_with_audio(
-        prompt,
-        nag_negative_prompt, nag_scale,
-        height=DEFAULT_H_SLIDER_VALUE, width=DEFAULT_W_SLIDER_VALUE, duration_seconds=DEFAULT_DURATION_SECONDS,
-        steps=DEFAULT_STEPS,
-        seed=DEFAULT_SEED, randomize_seed=False,
-        enable_audio=True, audio_negative_prompt=DEFAULT_AUDIO_NEGATIVE_PROMPT,
-        audio_steps=25, audio_cfg_strength=4.5,
+       prompt,
+       nag_negative_prompt, nag_scale,
+       height=DEFAULT_H_SLIDER_VALUE, width=DEFAULT_W_SLIDER_VALUE, duration_seconds=DEFAULT_DURATION_SECONDS,
+       steps=DEFAULT_STEPS,
+       seed=DEFAULT_SEED, randomize_seed=False,
+       enable_audio=True, audio_custom_prompt="",
+       audio_negative_prompt=DEFAULT_AUDIO_NEGATIVE_PROMPT,
+       audio_steps=30, audio_cfg_strength=4.5,
 ):
-    if pipe is None:
-        return None, DEFAULT_SEED
-        
-    try:
-        # Generate video first
-        target_h = max(MOD_VALUE, (int(height) // MOD_VALUE) * MOD_VALUE)
-        target_w = max(MOD_VALUE, (int(width) // MOD_VALUE) * MOD_VALUE)
-        
-        num_frames = np.clip(int(round(int(duration_seconds) * FIXED_FPS) + 1), MIN_FRAMES_MODEL, MAX_FRAMES_MODEL)
-        
-        current_seed = random.randint(0, MAX_SEED) if randomize_seed else int(seed)
-        
-        print(f"Generating video with: prompt='{prompt}', resolution={target_w}x{target_h}, frames={num_frames}")
-        
-        with torch.inference_mode():
-            nag_output_frames_list = pipe(
-                prompt=prompt,
-                nag_negative_prompt=nag_negative_prompt,
-                nag_scale=nag_scale,
-                nag_tau=3.5,
-                nag_alpha=0.5,
-                height=target_h, width=target_w, num_frames=num_frames,
-                guidance_scale=0.,
-                num_inference_steps=int(steps),
-                generator=torch.Generator(device="cuda").manual_seed(current_seed)
-            ).frames[0]
-        
-        # Save initial video without audio
-        with tempfile.NamedTemporaryFile(suffix=".mp4", delete=False) as tmpfile:
-            temp_video_path = tmpfile.name
-        export_to_video(nag_output_frames_list, temp_video_path, fps=FIXED_FPS)
-        print(f"Video saved to: {temp_video_path}")
-        
-        # Add audio if enabled
-        if enable_audio:
-            try:
-                print("Adding audio to video...")
-                final_video_path = add_audio_to_video(
-                    temp_video_path, 
-                    prompt,  # Use the same prompt for audio generation
-                    audio_negative_prompt,
-                    audio_steps,
-                    audio_cfg_strength,
-                    duration_seconds
-                )
-                # Clean up temp video
-                if os.path.exists(temp_video_path) and final_video_path != temp_video_path:
-                    os.remove(temp_video_path)
-                print(f"Final video with audio: {final_video_path}")
-            except Exception as e:
-                log.error(f"Audio generation failed: {e}")
-                final_video_path = temp_video_path
-        else:
-            final_video_path = temp_video_path
-        
-        return final_video_path, current_seed
-    except Exception as e:
-        print(f"Error in video generation: {e}")
-        return None, current_seed
+   if pipe is None:
+       return None, DEFAULT_SEED
+       
+   try:
+       # Generate video first
+       target_h = max(MOD_VALUE, (int(height) // MOD_VALUE) * MOD_VALUE)
+       target_w = max(MOD_VALUE, (int(width) // MOD_VALUE) * MOD_VALUE)
+       
+       num_frames = np.clip(int(round(int(duration_seconds) * FIXED_FPS) + 1), MIN_FRAMES_MODEL, MAX_FRAMES_MODEL)
+       
+       current_seed = random.randint(0, MAX_SEED) if randomize_seed else int(seed)
+       
+       print(f"Generating video with: prompt='{prompt}', resolution={target_w}x{target_h}, frames={num_frames}")
+       
+       with torch.inference_mode():
+           nag_output_frames_list = pipe(
+               prompt=prompt,
+               nag_negative_prompt=nag_negative_prompt,
+               nag_scale=nag_scale,
+               nag_tau=3.5,
+               nag_alpha=0.5,
+               height=target_h, width=target_w, num_frames=num_frames,
+               guidance_scale=0.,
+               num_inference_steps=int(steps),
+               generator=torch.Generator(device="cuda").manual_seed(current_seed)
+           ).frames[0]
+       
+       # Save initial video without audio
+       with tempfile.NamedTemporaryFile(suffix=".mp4", delete=False) as tmpfile:
+           temp_video_path = tmpfile.name
+       export_to_video(nag_output_frames_list, temp_video_path, fps=FIXED_FPS)
+       print(f"Video saved to: {temp_video_path}")
+       
+       # Add audio if enabled
+       if enable_audio:
+           try:
+               print("Adding audio to video...")
+               final_video_path = add_audio_to_video(
+                   temp_video_path, 
+                   prompt,
+                   audio_custom_prompt,
+                   audio_negative_prompt,
+                   audio_steps,
+                   audio_cfg_strength,
+                   duration_seconds
+               )
+               # Clean up temp video
+               if os.path.exists(temp_video_path) and final_video_path != temp_video_path:
+                   os.remove(temp_video_path)
+               print(f"Final video with audio: {final_video_path}")
+           except Exception as e:
+               log.error(f"Audio generation failed: {e}")
+               final_video_path = temp_video_path
+       else:
+           final_video_path = temp_video_path
+       
+       return final_video_path, current_seed
+   except Exception as e:
+       print(f"Error in video generation: {e}")
+       return None, current_seed
 
 # Example generation function - simplified
 def set_example(prompt, nag_negative_prompt, nag_scale):
-    """Set example values in the UI without triggering generation"""
-    return (
-        prompt,
-        nag_negative_prompt,
-        nag_scale,
-        DEFAULT_H_SLIDER_VALUE,
-        DEFAULT_W_SLIDER_VALUE,
-        DEFAULT_DURATION_SECONDS,
-        DEFAULT_STEPS,
-        DEFAULT_SEED,
-        True,  # randomize_seed
-        True,  # enable_audio
-        DEFAULT_AUDIO_NEGATIVE_PROMPT,
-        25,    # audio_steps
-        4.5    # audio_cfg_strength
-    )
+   """Set example values in the UI without triggering generation"""
+   return (
+       prompt,
+       nag_negative_prompt,
+       nag_scale,
+       DEFAULT_H_SLIDER_VALUE,
+       DEFAULT_W_SLIDER_VALUE,
+       DEFAULT_DURATION_SECONDS,
+       DEFAULT_STEPS,
+       DEFAULT_SEED,
+       True,  # randomize_seed
+       True,  # enable_audio
+       "",    # audio_custom_prompt
+       DEFAULT_AUDIO_NEGATIVE_PROMPT,
+       30,    # audio_steps
+       4.5    # audio_cfg_strength
+   )
 
 # Examples with audio descriptions
 examples = [
-    ["Midnight highway outside a neon-lit city. A black 1973 Porsche 911 Carrera RS speeds at 120 km/h. Inside, a stylish singer-guitarist sings while driving, vintage sunburst guitar on the passenger seat. Sodium streetlights streak over the hood; RGB panels shift magenta to blue on the driver. Camera: drone dive, Russian-arm low wheel shot, interior gimbal, FPV barrel roll, overhead spiral. Neo-noir palette, rain-slick asphalt reflections, roaring flat-six engine blended with live guitar.", DEFAULT_NAG_NEGATIVE_PROMPT, 11],
-    ["Arena rock concert packed with 20 000 fans. A flamboyant lead guitarist in leather jacket and mirrored aviators shreds a cherry-red Flying V on a thrust stage. Pyro flames shoot up on every downbeat, CO₂ jets burst behind. Moving-head spotlights swirl teal and amber, follow-spots rim-light the guitarist's hair. Steadicam 360-orbit, crane shot rising over crowd, ultra-slow-motion pick attack at 1 000 fps. Film-grain teal-orange grade, thunderous crowd roar mixes with screaming guitar solo.", DEFAULT_NAG_NEGATIVE_PROMPT, 11],
-    ["Golden-hour countryside road winding through rolling wheat fields. A man and woman ride a vintage café-racer motorcycle, hair and scarf fluttering in the warm breeze. Drone chase shot reveals endless patchwork farmland; low slider along rear wheel captures dust trail. Sun-flare back-lights the riders, lens blooms on highlights. Soft acoustic rock underscore; engine rumble mixed at –8 dB. Warm pastel color grade, gentle film-grain for nostalgic vibe.", DEFAULT_NAG_NEGATIVE_PROMPT, 11],
+   ["Midnight highway outside a neon-lit city. A black 1973 Porsche 911 Carrera RS speeds at 120 km/h. Inside, a stylish singer-guitarist sings while driving, vintage sunburst guitar on the passenger seat. Sodium streetlights streak over the hood; RGB panels shift magenta to blue on the driver. Camera: drone dive, Russian-arm low wheel shot, interior gimbal, FPV barrel roll, overhead spiral. Neo-noir palette, rain-slick asphalt reflections, roaring flat-six engine blended with live guitar.", DEFAULT_NAG_NEGATIVE_PROMPT, 11],
+   ["Arena rock concert packed with 20 000 fans. A flamboyant lead guitarist in leather jacket and mirrored aviators shreds a cherry-red Flying V on a thrust stage. Pyro flames shoot up on every downbeat, CO₂ jets burst behind. Moving-head spotlights swirl teal and amber, follow-spots rim-light the guitarist's hair. Steadicam 360-orbit, crane shot rising over crowd, ultra-slow-motion pick attack at 1 000 fps. Film-grain teal-orange grade, thunderous crowd roar mixes with screaming guitar solo.", DEFAULT_NAG_NEGATIVE_PROMPT, 11],
+   ["Golden-hour countryside road winding through rolling wheat fields. A man and woman ride a vintage café-racer motorcycle, hair and scarf fluttering in the warm breeze. Drone chase shot reveals endless patchwork farmland; low slider along rear wheel captures dust trail. Sun-flare back-lights the riders, lens blooms on highlights. Soft acoustic rock underscore; engine rumble mixed at –8 dB. Warm pastel color grade, gentle film-grain for nostalgic vibe.", DEFAULT_NAG_NEGATIVE_PROMPT, 11],
 ]
 
 # CSS styling - Fixed for better layout
 css = """
 /* Right column - video output */
 .video-output {
-    border-radius: 15px;
-    overflow: hidden;
-    box-shadow: 0 10px 30px rgba(0, 0, 0, 0.2);
-    width: 100% !important;
-    height: auto !important;
-    min-height: 400px;
+   border-radius: 15px;
+   overflow: hidden;
+   box-shadow: 0 10px 30px rgba(0, 0, 0, 0.2);
+   width: 100% !important;
+   height: auto !important;
+   min-height: 400px;
 }
 
 /* Ensure video container is responsive */
 .video-output video {
-    width: 100% !important;
-    height: auto !important;
-    max-height: 600px;
-    object-fit: contain;
-    display: block;
+   width: 100% !important;
+   height: auto !important;
+   max-height: 600px;
+   object-fit: contain;
+   display: block;
 }
 
 /* Remove any overlay or background from video container */
 .video-output > div {
-    background: transparent !important;
-    padding: 0 !important;
+   background: transparent !important;
+   padding: 0 !important;
 }
 
 /* Remove gradio's default video player overlay */
 .video-output .wrap {
-    background: transparent !important;
+   background: transparent !important;
 }
 
 /* Ensure no gray overlay on video controls */
 .video-output video::-webkit-media-controls-enclosure {
-    background: transparent;
+   background: transparent;
 }
 """
 
 # Gradio interface - Fixed structure
 with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
-    gr.HTML("""
-        <div class="container">
-            <h1 class="main-title">🎬 VEO3 Free</h1>
-            <p class="subtitle">Wan2.1-T2V-14B + Fast 4-step with NAG + Automatic Audio Generation</p>
-        </div>
-    """)
-    
-    gr.HTML("""
-        <div class='container' style='display:flex; justify-content:center; gap:12px; margin-bottom: 20px;'>
-            <a href="https://huggingface.co/spaces/openfree/Best-AI" target="_blank">
-                <img src="https://img.shields.io/static/v1?label=OpenFree&message=BEST%20AI%20Services&color=%230000ff&labelColor=%23000080&logo=huggingface&logoColor=%23ffa500&style=for-the-badge" alt="OpenFree badge">
-            </a>
-
-            <a href="https://discord.gg/openfreeai" target="_blank">
-                <img src="https://img.shields.io/static/v1?label=Discord&message=Openfree%20AI&color=%230000ff&labelColor=%23800080&logo=discord&logoColor=white&style=for-the-badge" alt="Discord badge">
-            </a>
-        </div>
-    """)
-    
-    with gr.Row(equal_height=True):
-        with gr.Column(scale=5):
-            with gr.Group(elem_classes="prompt-container"):
-                prompt = gr.Textbox(
-                    label="✨ Video Prompt (also used for audio generation)",
-                    placeholder="Describe your video scene in detail...",
-                    lines=3,
-                    elem_classes="prompt-input"
-                )
-                
-                with gr.Accordion("🎨 Advanced Video Settings", open=False):
-                    nag_negative_prompt = gr.Textbox(
-                        label="Video Negative Prompt",
-                        value=DEFAULT_NAG_NEGATIVE_PROMPT,
-                        lines=2,
-                    )
-                    nag_scale = gr.Slider(
-                        label="NAG Scale",
-                        minimum=1.0,
-                        maximum=20.0,
-                        step=0.25,
-                        value=11.0,
-                        info="Higher values = stronger guidance"
-                    )
-            
-            with gr.Group(elem_classes="settings-panel"):
-                gr.Markdown("### ⚙️ Video Settings")
-                
-                with gr.Row():
-                    duration_seconds_input = gr.Slider(
-                        minimum=1,
-                        maximum=8,
-                        step=1,
-                        value=DEFAULT_DURATION_SECONDS,
-                        label="📱 Duration (seconds)",
-                        elem_classes="slider-container"
-                    )
-                    steps_slider = gr.Slider(
-                        minimum=1,
-                        maximum=8,
-                        step=1,
-                        value=DEFAULT_STEPS,
-                        label="🔄 Inference Steps",
-                        elem_classes="slider-container"
-                    )
-                
-                with gr.Row():
-                    height_input = gr.Slider(
-                        minimum=SLIDER_MIN_H,
-                        maximum=SLIDER_MAX_H,
-                        step=MOD_VALUE,
-                        value=DEFAULT_H_SLIDER_VALUE,
-                        label=f"📐 Height (×{MOD_VALUE})",
-                        elem_classes="slider-container"
-                    )
-                    width_input = gr.Slider(
-                        minimum=SLIDER_MIN_W,
-                        maximum=SLIDER_MAX_W,
-                        step=MOD_VALUE,
-                        value=DEFAULT_W_SLIDER_VALUE,
-                        label=f"📐 Width (×{MOD_VALUE})",
-                        elem_classes="slider-container"
-                    )
-                
-                with gr.Row():
-                    seed_input = gr.Slider(
-                        label="🌱 Seed",
-                        minimum=0,
-                        maximum=MAX_SEED,
-                        step=1,
-                        value=DEFAULT_SEED,
-                        interactive=True
-                    )
-                    randomize_seed_checkbox = gr.Checkbox(
-                        label="🎲 Random Seed",
-                        value=True,
-                        interactive=True
-                    )
-            
-            with gr.Group(elem_classes="audio-settings"):
-                gr.Markdown("### 🎵 Audio Generation Settings")
-                
-                enable_audio = gr.Checkbox(
-                    label="🔊 Enable Automatic Audio Generation",
-                    value=True,
-                    interactive=True
-                )
-                
-                with gr.Column(visible=True) as audio_settings_group:
-                    audio_negative_prompt = gr.Textbox(
-                        label="Audio Negative Prompt",
-                        value=DEFAULT_AUDIO_NEGATIVE_PROMPT,
-                        placeholder="Elements to avoid in audio (e.g., music, speech)",
-                    )
-                    
-                    with gr.Row():
-                        audio_steps = gr.Slider(
-                            minimum=10,
-                            maximum=50,
-                            step=5,
-                            value=25,
-                            label="🎚️ Audio Steps",
-                            info="More steps = better quality"
-                        )
-                        audio_cfg_strength = gr.Slider(
-                            minimum=1.0,
-                            maximum=10.0,
-                            step=0.5,
-                            value=4.5,
-                            label="🎛️ Audio Guidance",
-                            info="Strength of prompt guidance"
-                        )
-                
-                # Toggle audio settings visibility
-                enable_audio.change(
-                    fn=lambda x: gr.update(visible=x),
-                    inputs=[enable_audio],
-                    outputs=[audio_settings_group]
-                )
-            
-            generate_button = gr.Button(
-                "🎬 Generate Video with Audio",
-                variant="primary",
-                elem_classes="generate-btn"
-            )
-        
-        with gr.Column(scale=5):
-            video_output = gr.Video(
-                label="Generated Video with Audio",
-                autoplay=True,
-                interactive=False,
-                elem_classes="video-output",
-                height=600
-            )
-            
-            gr.HTML("""
-                <div style="text-align: center; margin-top: 20px; color: #6b7280;">
-                    <p>💡 Tip: The same prompt is used for both video and audio generation!</p>
-                    <p>🎧 Audio is automatically matched to the visual content</p>
-                </div>
-            """)
-    
-    # Examples section moved outside of columns
-    with gr.Row():
-        gr.Markdown("### 🎯 Example Prompts")
-    
-    gr.Examples(
-        examples=examples,
-        inputs=[prompt, nag_negative_prompt, nag_scale],
-        outputs=None,  # Don't connect outputs to avoid index issues
-        cache_examples=False
-    )
-    
-    # Connect UI elements
-    ui_inputs = [
-        prompt,
-        nag_negative_prompt, nag_scale,
-        height_input, width_input, duration_seconds_input,
-        steps_slider,
-        seed_input, randomize_seed_checkbox,
-        enable_audio, audio_negative_prompt, audio_steps, audio_cfg_strength,
-    ]
-    
-    generate_button.click(
-        fn=generate_video_with_audio,
-        inputs=ui_inputs,
-        outputs=[video_output, seed_input],
-    )
+   gr.HTML("""
+       <div class="container">
+           <h1 class="main-title">🎬 VEO3 Free</h1>
+           <p class="subtitle">Wan2.1-T2V-14B + Fast 4-step with NAG + Automatic Audio Generation</p>
+       </div>
+   """)
+   
+   gr.HTML("""
+       <div class='container' style='display:flex; justify-content:center; gap:12px; margin-bottom: 20px;'>
+           <a href="https://huggingface.co/spaces/openfree/Best-AI" target="_blank">
+               <img src="https://img.shields.io/static/v1?label=OpenFree&message=BEST%20AI%20Services&color=%230000ff&labelColor=%23000080&logo=huggingface&logoColor=%23ffa500&style=for-the-badge" alt="OpenFree badge">
+           </a>
+
+           <a href="https://discord.gg/openfreeai" target="_blank">
+               <img src="https://img.shields.io/static/v1?label=Discord&message=Openfree%20AI&color=%230000ff&labelColor=%23800080&logo=discord&logoColor=white&style=for-the-badge" alt="Discord badge">
+           </a>
+       </div>
+   """)
+   
+   with gr.Row(equal_height=True):
+       with gr.Column(scale=5):
+           with gr.Group(elem_classes="prompt-container"):
+               prompt = gr.Textbox(
+                   label="✨ Video Prompt (also used for audio generation)",
+                   placeholder="Describe your video scene in detail...",
+                   lines=3,
+                   elem_classes="prompt-input"
+               )
+               
+               with gr.Accordion("🎨 Advanced Video Settings", open=False):
+                   nag_negative_prompt = gr.Textbox(
+                       label="Video Negative Prompt",
+                       value=DEFAULT_NAG_NEGATIVE_PROMPT,
+                       lines=2,
+                   )
+                   nag_scale = gr.Slider(
+                       label="NAG Scale",
+                       minimum=1.0,
+                       maximum=20.0,
+                       step=0.25,
+                       value=11.0,
+                       info="Higher values = stronger guidance"
+                   )
+           
+           with gr.Group(elem_classes="settings-panel"):
+               gr.Markdown("### ⚙️ Video Settings")
+               
+               with gr.Row():
+                   duration_seconds_input = gr.Slider(
+                       minimum=1,
+                       maximum=8,
+                       step=1,
+                       value=DEFAULT_DURATION_SECONDS,
+                       label="📱 Duration (seconds)",
+                       elem_classes="slider-container"
+                   )
+                   steps_slider = gr.Slider(
+                       minimum=1,
+                       maximum=8,
+                       step=1,
+                       value=DEFAULT_STEPS,
+                       label="🔄 Inference Steps",
+                       elem_classes="slider-container"
+                   )
+               
+               with gr.Row():
+                   height_input = gr.Slider(
+                       minimum=SLIDER_MIN_H,
+                       maximum=SLIDER_MAX_H,
+                       step=MOD_VALUE,
+                       value=DEFAULT_H_SLIDER_VALUE,
+                       label=f"📐 Height (×{MOD_VALUE})",
+                       elem_classes="slider-container"
+                   )
+                   width_input = gr.Slider(
+                       minimum=SLIDER_MIN_W,
+                       maximum=SLIDER_MAX_W,
+                       step=MOD_VALUE,
+                       value=DEFAULT_W_SLIDER_VALUE,
+                       label=f"📐 Width (×{MOD_VALUE})",
+                       elem_classes="slider-container"
+                   )
+               
+               with gr.Row():
+                   seed_input = gr.Slider(
+                       label="🌱 Seed",
+                       minimum=0,
+                       maximum=MAX_SEED,
+                       step=1,
+                       value=DEFAULT_SEED,
+                       interactive=True
+                   )
+                   randomize_seed_checkbox = gr.Checkbox(
+                       label="🎲 Random Seed",
+                       value=True,
+                       interactive=True
+                   )
+           
+           with gr.Group(elem_classes="audio-settings"):
+               gr.Markdown("### 🎵 Audio Generation Settings")
+               
+               enable_audio = gr.Checkbox(
+                   label="🔊 Enable Automatic Audio Generation",
+                   value=True,
+                   interactive=True
+               )
+               
+               with gr.Column(visible=True) as audio_settings_group:
+                   audio_custom_prompt = gr.Textbox(
+                       label="Custom Audio Prompt (Optional)",
+                       placeholder="Leave empty to auto-generate from video prompt, or specify custom audio description (e.g., 'car engine sound, traffic noise')",
+                       value="",
+                   )
+                   audio_negative_prompt = gr.Textbox(
+                       label="Audio Negative Prompt",
+                       value=DEFAULT_AUDIO_NEGATIVE_PROMPT,
+                       placeholder="Elements to avoid in audio",
+                   )
+                   
+                   with gr.Row():
+                       audio_steps = gr.Slider(
+                           minimum=10,
+                           maximum=50,
+                           step=5,
+                           value=30,
+                           label="🎚️ Audio Steps",
+                           info="More steps = better quality"
+                       )
+                       audio_cfg_strength = gr.Slider(
+                           minimum=1.0,
+                           maximum=10.0,
+                           step=0.5,
+                           value=4.5,
+                           label="🎛️ Audio Guidance",
+                           info="Strength of prompt guidance"
+                       )
+               
+               # Toggle audio settings visibility
+               enable_audio.change(
+                   fn=lambda x: gr.update(visible=x),
+                   inputs=[enable_audio],
+                   outputs=[audio_settings_group]
+               )
+           
+           generate_button = gr.Button(
+               "🎬 Generate Video with Audio",
+               variant="primary",
+               elem_classes="generate-btn"
+           )
+       
+       with gr.Column(scale=5):
+           video_output = gr.Video(
+               label="Generated Video with Audio",
+               autoplay=True,
+               interactive=False,
+               elem_classes="video-output",
+               height=600
+           )
+           
+           gr.HTML("""
+               <div style="text-align: center; margin-top: 20px; color: #6b7280;">
+                   <p>💡 Tip: For better audio, use Custom Audio Prompt with sound descriptions!</p>
+                   <p>🎧 Examples: "car engine sound", "crowd cheering", "nature ambience"</p>
+               </div>
+           """)
+   
+   # Examples section moved outside of columns
+   with gr.Row():
+       gr.Markdown("### 🎯 Example Prompts")
+   
+   gr.Examples(
+       examples=examples,
+       inputs=[prompt, nag_negative_prompt, nag_scale],
+       outputs=None,  # Don't connect outputs to avoid index issues
+       cache_examples=False
+   )
+   
+   # Connect UI elements
+   ui_inputs = [
+       prompt,
+       nag_negative_prompt, nag_scale,
+       height_input, width_input, duration_seconds_input,
+       steps_slider,
+       seed_input, randomize_seed_checkbox,
+       enable_audio, audio_custom_prompt, audio_negative_prompt, 
+       audio_steps, audio_cfg_strength,
+   ]
+   
+   generate_button.click(
+       fn=generate_video_with_audio,
+       inputs=ui_inputs,
+       outputs=[video_output, seed_input],
+   )
 
 if __name__ == "__main__":
-    demo.queue().launch( allowed_paths=["/","/tmp","/tmp/gradio"] )
+       demo.queue().launch( allowed_paths=["/","/tmp","/tmp/gradio"] )