Upload app.py

app.py

@@ -0,0 +1,119 @@
+import imageio
+import imageio.v3 as iio
+import numpy as np
+import matplotlib.pyplot as plt
+import matplotlib.animation as animation
+from skimage.transform import resize
+from IPython.display import HTML
+import asyncio
+import warnings
+from demo import load_checkpoints
+import torch
+from animate import normalize_kp
+from skimage import img_as_ubyte
+from tqdm import tqdm
+from scipy.spatial import ConvexHull
+from urllib.request import Request, urlopen
+from nextcord import Interaction, SlashOption, ChannelType
+from nextcord.abc import GuildChannel
+from nextcord.ext import commands
+import nextcord
+
+client = commands.Bot(command_prefix='!')
+testigaerverid=989256818398203945
+#aaaaaaaaaaaa
+def find_best_frame(source, driving, cpu=False):
+    import face_alignment
+
+    def normalize_kp(kp):
+        kp = kp - kp.mean(axis=0, keepdims=True)
+        area = ConvexHull(kp[:, :2]).volume
+        area = np.sqrt(area)
+        kp[:, :2] = kp[:, :2] / area
+        return kp
+
+    fa = face_alignment.FaceAlignment(face_alignment.LandmarksType._2D, flip_input=True,
+                                device='cpu' if cpu else 'cuda')
+    kp_source = fa.get_landmarks(255 * source)[0]
+    kp_source = normalize_kp(kp_source)
+    norm  = float('inf')
+    frame_num = 0
+    for i, image in tqdm(enumerate(driving)):
+        kp_driving = fa.get_landmarks(255 * image)[0]
+        kp_driving = normalize_kp(kp_driving)
+        new_norm = (np.abs(kp_source - kp_driving) ** 2).sum()
+        if new_norm < norm:
+            norm = new_norm
+            frame_num = i
+        return frame_num
+#sssssssssssss
+def display(source, driving, generated=None):
+    fig = plt.figure(figsize=(8 + 4 * (generated is not None), 6))
+
+    ims = []
+    for i in range(len(driving)):
+        cols = [source]
+        cols.append(driving[i])
+        if generated is not None:
+            cols.append(generated[i])
+        im = plt.imshow(np.concatenate(cols, axis=1), animated=True)
+        plt.axis('off')
+        ims.append([im])
+
+    ani = animation.ArtistAnimation(fig, ims, interval=50, repeat_delay=1000)
+    plt.close()
+    return ani
+#Resize image and video to 256x256
+def dy():
+    for i in range( 10):
+        i=i+1
+        time.sleep(5)
+        yield str(i)
+
+
+@client.slash_command(name="repeat", description="whatever doyou want",guild_ids=[testigaerverid])
+async def repeat(interaction : Interaction, message:str, message2:str):
+    channel = interaction.channel
+    await interaction.response.send_message("jj")
+    warnings.filterwarnings("ignore")
+    web_image = message
+    request_site = Request(web_image, headers={"User-Agent": "Mozilla/5.0"})
+    source_image =iio.imread(urlopen(request_site).read())
+    urlforvideo=message2
+    driving_video = iio.imread(urlforvideo)
+    source_image = resize(source_image, (256, 256))[..., :3]
+    driving_video = [resize(frame, (256, 256))[..., :3] for frame in driving_video]
+    eg,cd=load_checkpoints('config//vox-256.yaml','vox-cpk.pth.tar',True)
+    cpu=True
+    print("came to  this")
+    with torch.no_grad():
+        predictions = []
+        source = torch.tensor(source_image[np.newaxis].astype(np.float32)).permute(0, 3, 1, 2)
+        if not cpu:
+            source = source.cuda()
+        driving = torch.tensor(np.array(driving_video)[np.newaxis].astype(np.float32)).permute(0, 4, 1, 2, 3)
+        kp_source = cd(source)
+        kp_driving_initial = cd(driving[:, :, 0])
+        progress_message = await channel.send("Progress: 0%")
+        for frame_idx in tqdm(range(driving.shape[2])):
+            
+            driving_frame = driving[:, :, frame_idx]
+            if not cpu:
+                driving_frame = driving_frame.cuda()
+            kp_driving = cd(driving_frame)
+            kp_norm = normalize_kp(kp_source=kp_source, kp_driving=kp_driving,
+                                    kp_driving_initial=kp_driving_initial, use_relative_movement=True,
+                                    use_relative_jacobian=True, adapt_movement_scale=True)
+            out = eg(source, kp_source=kp_source, kp_driving=kp_norm)
+            predictions.append(np.transpose(out['prediction'].data.cpu().numpy(), [0, 2, 3, 1])[0])
+            await progress_message.edit(content=f"{frame_idx}")
+
+    print("print karandath puluvan bola")
+    imageio.mimsave('../generated.mp4', [img_as_ubyte(frame) for frame in predictions])
+@client.event
+async def on_ready():
+    print("Bot is connected") 
+   
+
+
+client.run("MTA1OTcwODIxNTY5MDAwNjU5OA.GjNyS_.QNudUyA7G-gHbMZPQDuPWIQdmldKFJOi5c6AdI")