fix: quota

app.py

@@ -290,7 +290,7 @@ def _parse_args():
     parser.add_argument(
         "--det_thresh",
         type=float,
-        default=0.12,
+        default=0.10,
         help="Threshold for InsightFace face detection.")
     parser.add_argument(
         "--mode",
@@ -605,11 +605,11 @@ def run_graio_demo(args):
     # 参考: https://huggingface.co/spaces/KlingTeam/LivePortrait/blob/main/app.py
     # @spaces.GPU 装饰器会自动处理 GPU 初始化，不需要手动初始化
     
-    # 快速生成模式：200秒，固定12步去噪
-    @spaces.GPU(duration=200)
+    # 快速生成模式：210秒，固定10步去噪
+    @spaces.GPU(duration=210)
     def gpu_wrapped_generate_video_fast(*args, **kwargs):
-        # 固定使用12步去噪，通过关键字参数传递
-        kwargs['fixed_steps'] = 12
+        # 固定使用10步去噪，通过关键字参数传递
+        kwargs['fixed_steps'] = 10
         return gpu_wrapped_generate_video_worker(*args, **kwargs)
     
     # 高质量生成模式：720秒，用户选择去噪步数
@@ -757,7 +757,7 @@ def run_graio_demo(args):
 
                 with gr.Row():
                     run_i2v_button_fast = gr.Button(
-                        "Generate Video (Fast - 200s, 12 steps)", 
+                        "Generate Video (Fast - 210s, 10 steps)", 
                         variant="secondary",
                         scale=1
                     )
@@ -768,10 +768,10 @@ def run_graio_demo(args):
                     )
                 gr.Markdown("""
                 **Generation Modes:**
-                - **Fast Mode (up to 200s GPU budget)**: Fixed 12 denoising steps for quick generation. Suitable for single-person videos or quick previews. The 200s is the maximum GPU allocation time, not the actual generation time.
+                - **Fast Mode (up to 210s GPU budget)**: Fixed 10 denoising steps for quick generation. Suitable for single-person videos or quick previews. The 210s is the maximum GPU allocation time, not the actual generation time.
                 - **Quality Mode (up to 720s GPU budget)**: Custom denoising steps (adjustable via "Diffusion steps" slider). Recommended for multi-person videos that require higher quality. The 720s is the maximum GPU allocation time, not the actual generation time. With 40 denoising steps, approximately 10 seconds of video can be generated.
                 
-                *Note: The GPU duration (200s/720s) represents the maximum budget allocated, not the actual generation time. Multi-person videos generally require longer duration and more Usage Quota for better quality.*
+                *Note: The GPU duration (210s/720s) represents the maximum budget allocated, not the actual generation time. Multi-person videos generally require longer duration and more Usage Quota for better quality.*
                 """)
 
             with gr.Column(scale=2):
@@ -806,7 +806,7 @@ def run_graio_demo(args):
                 )
 
 
-        # 快速生成按钮：200秒，固定12步
+        # 快速生成按钮：210秒，固定10步
         run_i2v_button_fast.click(
             fn=gpu_wrapped_generate_video_fast,
             inputs=[img2vid_image, img2vid_prompt, n_prompt, img2vid_audio_1, img2vid_audio_2, img2vid_audio_3, sd_steps, seed, guide_scale, person_num_selector, audio_mode_selector],