Commit message: Added support for hardware accelerators in ffmpeg. #5

app.py

@@ -37,8 +37,8 @@ with gr.Blocks() as demo:
     with gr.Row():
         gr.Markdown("# Refacer")
     with gr.Row():
-        video=gr.Video(label="Original video")
+        video=gr.Video(label="Original video",format="mp4")
-        video2=gr.Video(label="Refaced video",interactive=False)
+        video2=gr.Video(label="Refaced video",interactive=False,format="mp4")
 
     for i in range(0,num_faces):
         with gr.Tab(f"Face #{i+1}"):

notebooks/Refacer_colab.ipynb

@@ -35,27 +35,14 @@
       "outputs": [],
       "source": [
         "!pip uninstall numpy -y -q\n",
-        "!pip install numpy==1.24.3 onnxruntime-gpu gradio insightface ffmpeg_python opencv_python -q --force\n",
+        "!pip install --disable-pip-version-check --root-user-action=ignore numpy==1.24.3 onnxruntime-gpu gradio insightface==0.7.3 ffmpeg_python opencv_python -q --force\n",
         "\n",
         "!git clone https://github.com/xaviviro/refacer.git\n",
         "%cd refacer\n",
         "\n",
-        "!wget --content-disposition \"https://huggingface.co/deepinsight/inswapper/resolve/main/inswapper_128.onnx\""
+        "!wget --content-disposition \"https://huggingface.co/deepinsight/inswapper/resolve/main/inswapper_128.onnx\"\n",
-      ]
+        "\n",
-    },
+        "!python app.py --share_gradio\n"
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "0SsyI3quBb0L",
-        "outputId": "56add1a6-6b47-429d-e07a-cf3fadc7a6ce"
-      },
-      "outputs": [],
-      "source": [
-        "!python app.py --share_gradio"
       ]
     }
   ],

refacer.py

@@ -18,6 +18,8 @@ import psutil
 from enum import Enum
 from insightface.app.common import Face
 from insightface.utils.storage import ensure_available
+import re
+import subprocess
 
 class RefacerMode(Enum):
      CPU, CUDA, COREML, TENSORRT = range(1, 5)
@@ -25,6 +27,7 @@ class RefacerMode(Enum):
 class Refacer:
     def __init__(self,force_cpu=False):
         self.force_cpu = force_cpu
+        self.__check_encoders()
         self.__check_providers()
         self.total_mem = psutil.virtual_memory().total
         self.__init_apps()
@@ -96,12 +99,14 @@ class Refacer:
 
         return replacements
     def __convert_video(self,video_path,output_video_path):
+        print("Merging audio with the refaced video...")
         new_path = output_video_path + str(random.randint(0,999)) + "_c.mp4"
         #stream = ffmpeg.input(output_video_path)
         in1 = ffmpeg.input(output_video_path)
         in2 = ffmpeg.input(video_path)
-        out = ffmpeg.output(in1.video, in2.audio, new_path,vcodec="libx264")
+        out = ffmpeg.output(in1.video, in2.audio, new_path,vcodec=self.ffmpeg_video_encoder)
-        out.run()
+        out.run(overwrite_output=True,quiet=True)
+        print(f"The process has finished.\nThe refaced video can be found at {os.path.abspath(new_path)}")
         return new_path
 
     def __get_faces(self,frame,max_num=0):
@@ -120,7 +125,7 @@ class Refacer:
             face.embedding = self.rec_app.get(frame, kps)
             ret.append(face)
         return ret
-    
+
     def __process_faces(self,frame):
         faces = self.__get_faces(frame)
         for face in faces:
@@ -168,4 +173,29 @@ class Refacer:
                 output.write(result)
             output.release()
 
-        return self.__convert_video(video_path,output_video_path)
+        return self.__convert_video(video_path,output_video_path)
+    
+    def __check_encoders(self):
+        self.ffmpeg_video_encoder="libx264"
+        pattern = r"encoders: ([a-zA-Z0-9_]+(?: [a-zA-Z0-9_]+)*)"
+        command = ['ffmpeg', '-codecs', '--list-encoders']
+        commandout = subprocess.run(command, check=True, capture_output=True).stdout
+        result = commandout.decode('utf-8').split('\n')
+        for r in result:
+            if "264" in r: 
+                encoders = re.search(pattern, r).group(1).split(' ')
+                #print(encoders)
+                for v_c in Refacer.VIDEO_CODECS:
+                    if v_c in encoders:
+                        self.ffmpeg_video_encoder=v_c
+                        break
+        print(f"Video codec for FFMPEG: {self.ffmpeg_video_encoder}")
+
+    VIDEO_CODECS = [
+         #'h264_videotoolbox', #osx HW acceleration
+         'h264_nvenc', #NVIDIA HW acceleration
+         #'h264_qsv', #Intel HW acceleration
+         #'h264_vaapi', #Intel HW acceleration
+         #'h264_omx', #HW acceleration
+         'libx264', #No HW acceleration
+    ]