Complete Video Subtitle Remover with Git LFS

.gitattributes

@@ -0,0 +1,5 @@
+*.pdiparams filter=lfs diff=lfs merge=lfs -text
+*.pdmodel filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

backend/models/V4/ch_det/inference.pdmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b2bd98be520804dae456a57a38707aa6051cb7cfd442b56cf85d92cc5a299b
+size 2203033

backend/models/V4/ch_det/inference_1.pdiparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b287157513150c1bc3c8489d7d975b255bdd13172118863d6bf2e5082f686594
+size 50000000

backend/models/V4/ch_det/inference_2.pdiparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e1994b0d2a8f9a47e62fdf55c2ca3c9f6ff06acd1f79cc8da44abbb9e44404
+size 50000000

backend/models/V4/ch_det/inference_3.pdiparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd34281a1cc220cc8ef094a4b935718686fa7eaef23ab77e6baac80badacc32
+size 13295054

backend/models/V4/ch_det_fast/inference.pdiparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ee815e30cff43cb1057d33bf0d94193e4d4f1ae28451cad15b40be830df915
+size 4692937

backend/models/V4/ch_det_fast/inference.pdmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad68ed2768fe6c41166a5bc64680cc9f445390acb6528da449a4db2f7b90e14
+size 166367

google_colabs/fix_notebook.py

@@ -0,0 +1,148 @@
+#!/usr/bin/env python3
+"""
+Update Colab notebook with new Stable Diffusion, DiffuEraser, and E2FGVI options
+"""
+import json
+
+# Read the notebook
+with open('Video_Subtitle_Remover.ipynb', 'r') as f:
+    nb = json.load(f)
+
+# 1. Update Step 3 - Add new dependencies
+for i, cell in enumerate(nb['cells']):
+    if cell['cell_type'] == 'code' and cell['source']:
+        source = ''.join(cell['source'])
+        if 'pip install -q filesplit==3.0.2' in source:
+            # Add diffusers and related packages
+            cell['source'] = [
+                "# Install dependencies\n",
+                "# Note: Colab already has torch, torchvision, opencv-python, numpy, etc.\n",
+                "!pip install -q filesplit==3.0.2 albumentations scikit-image imgaug pyclipper lmdb\n",
+                "!pip install -q PyYAML omegaconf tqdm easydict scikit-learn pandas webdataset\n",
+                "!pip install -q protobuf av einops paddleocr paddle2onnx onnxruntime-gpu\n",
+                "\n",
+                "# Install PaddlePaddle GPU version (compatible with Colab)\n",
+                "!pip install -q paddlepaddle-gpu==2.6.2\n",
+                "\n",
+                "# Advanced Inpainting Models (Optional - only install if using these modes)\n",
+                "# Uncomment the line below to enable Stable Diffusion, DiffuEraser, E2FGVI\n",
+                "# !pip install -q diffusers transformers accelerate\n",
+                "\n",
+                "print(\"✓ Dependencies installed!\")"
+            ]
+            print(f"✓ Updated Step 3 (Cell {i}): Added advanced model dependencies")
+            break
+
+# 2. Update Step 5 - Add new algorithm options
+for i, cell in enumerate(nb['cells']):
+    if cell['cell_type'] == 'code' and cell['source']:
+        source = ''.join(cell['source'])
+        if 'ALGORITHM =' in source and '# === CONFIGURATION ===' in source:
+            cell['source'] = [
+                "# === CONFIGURATION ===\n",
+                "\n",
+                "# Algorithm selection\n",
+                "# Options:\n",
+                "#   'STTN' - Fast, real-time video (recommended for Colab)\n",
+                "#   'LAMA' - High quality for images/animation\n",
+                "#   'PROPAINTER' - Best quality, very slow, high VRAM\n",
+                "#   'SD' - Stable Diffusion (NEW - requires extra install above)\n",
+                "#   'DIFFUERASER' - Specialized subtitle removal (Coming soon)\n",
+                "#   'E2FGVI' - Fast flow-guided (Coming soon)\n",
+                "ALGORITHM = 'STTN'\n",
+                "\n",
+                "# STTN Settings (recommended for Colab)\n",
+                "STTN_SKIP_DETECTION = True  # Much faster, processes entire subtitle area\n",
+                "STTN_MAX_LOAD_NUM = 40      # Reduce if OOM (30-50 for T4 GPU)\n",
+                "STTN_NEIGHBOR_STRIDE = 5\n",
+                "STTN_REFERENCE_LENGTH = 10\n",
+                "\n",
+                "# LAMA Settings\n",
+                "LAMA_SUPER_FAST = False     # Set True for faster but lower quality\n",
+                "\n",
+                "# ProPainter Settings (requires 16GB+ GPU, not recommended for Colab)\n",
+                "PROPAINTER_MAX_LOAD_NUM = 40  # Very low for T4 GPU\n",
+                "\n",
+                "# Stable Diffusion Settings (NEW)\n",
+                "SD_STEPS = 50                # More steps = better quality but slower\n",
+                "SD_GUIDANCE_SCALE = 7.5      # How much to follow the prompt\n",
+                "SD_PROMPT = \"natural scene, high quality\"  # Text guidance\n",
+                "\n",
+                "# Video path (change this)\n",
+                "# Option 1: Use sample video\n",
+                "VIDEO_PATH = '/content/video-subtitle-remover/test/test.mp4'\n",
+                "\n",
+                "# Option 2: Use video from Google Drive (uncomment)\n",
+                "# VIDEO_PATH = '/content/drive/MyDrive/my_video.mp4'\n",
+                "\n",
+                "# Subtitle area (optional, in pixels: ymin, ymax, xmin, xmax)\n",
+                "# None = auto-detect subtitle area\n",
+                "SUBTITLE_AREA = None\n",
+                "\n",
+                "# Example: Bottom 20% of 1080p video\n",
+                "# SUBTITLE_AREA = (864, 1080, 0, 1920)\n",
+                "\n",
+                "print(f\"Configuration:\")\n",
+                "print(f\"  Algorithm: {ALGORITHM}\")\n",
+                "print(f\"  Video: {VIDEO_PATH}\")\n",
+                "print(f\"  Subtitle area: {SUBTITLE_AREA or 'Auto-detect'}\")"
+            ]
+            print(f"✓ Updated Step 5 (Cell {i}): Added SD/DiffuEraser/E2FGVI options")
+            break
+
+# 3. Update Step 6 - Handle new algorithms
+for i, cell in enumerate(nb['cells']):
+    if cell['cell_type'] == 'code' and cell['source']:
+        source = ''.join(cell['source'])
+        if 'config.MODE = InpaintMode.STTN' in source:
+            cell['source'] = [
+                "# Modify config.py with our settings\n",
+                "import sys\n",
+                "sys.path.insert(0, '/content/video-subtitle-remover')\n",
+                "sys.path.insert(0, '/content/video-subtitle-remover/backend')\n",
+                "\n",
+                "from backend import config\n",
+                "from backend.config import InpaintMode\n",
+                "\n",
+                "# Apply algorithm selection\n",
+                "if ALGORITHM == 'STTN':\n",
+                "    config.MODE = InpaintMode.STTN\n",
+                "    config.STTN_SKIP_DETECTION = STTN_SKIP_DETECTION\n",
+                "    config.STTN_MAX_LOAD_NUM = STTN_MAX_LOAD_NUM\n",
+                "    config.STTN_NEIGHBOR_STRIDE = STTN_NEIGHBOR_STRIDE\n",
+                "    config.STTN_REFERENCE_LENGTH = STTN_REFERENCE_LENGTH\n",
+                "elif ALGORITHM == 'LAMA':\n",
+                "    config.MODE = InpaintMode.LAMA\n",
+                "    config.LAMA_SUPER_FAST = LAMA_SUPER_FAST\n",
+                "elif ALGORITHM == 'PROPAINTER':\n",
+                "    config.MODE = InpaintMode.PROPAINTER\n",
+                "    config.PROPAINTER_MAX_LOAD_NUM = PROPAINTER_MAX_LOAD_NUM\n",
+                "elif ALGORITHM == 'SD':\n",
+                "    config.MODE = InpaintMode.STABLE_DIFFUSION\n",
+                "    config.SD_STEPS = SD_STEPS\n",
+                "    config.SD_GUIDANCE_SCALE = SD_GUIDANCE_SCALE\n",
+                "    config.SD_PROMPT = SD_PROMPT\n",
+                "elif ALGORITHM == 'DIFFUERASER':\n",
+                "    config.MODE = InpaintMode.DIFFUERASER\n",
+                "    print('⚠️  DiffuEraser not yet implemented, will fall back to LAMA')\n",
+                "elif ALGORITHM == 'E2FGVI':\n",
+                "    config.MODE = InpaintMode.E2FGVI\n",
+                "    print('⚠️  E2FGVI not yet implemented, will fall back to STTN')\n",
+                "\n",
+                "print(f\"✓ Configuration applied!\")\n",
+                "print(f\"  Using device: {config.device}\")\n",
+                "print(f\"  Mode: {config.MODE.value}\")"
+            ]
+            print(f"✓ Updated Step 6 (Cell {i}): Added new algorithm handling")
+            break
+
+# Save the notebook
+with open('Video_Subtitle_Remover.ipynb', 'w') as f:
+    json.dump(nb, f, indent=1, ensure_ascii=False)
+
+print("\n✓ Colab notebook updated!")
+print("\nChanges made:")
+print("  1. Step 3: Added diffusers/transformers (commented out by default)")
+print("  2. Step 5: Added SD, DiffuEraser, E2FGVI options")
+print("  3. Step 5: Added SD configuration parameters")
+print("  4. Step 6: Added handling for new algorithms")

test/test.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c6bb6f2bd0fff4af75f7b3ec969ec976f8ca9c2c86687c6117598069139a66
+size 5335235

test/test1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b347ac0d0dd4a6e8e2b999727aaf44620227614742054681d3e20c28dc75a2
+size 5596517

test/test2.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c1f33de3957436dde22dcecf4e19c1ecf8252f5c544ecdb6f565b44e26d0ff6
+size 914010

test/test3.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1458093ddc57da7d8d52ec584ad22935eadb5d474a1ec9a7d0cfda8f835390a
+size 4438677

test/test4.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5b2ed88800f8a878f01d10d38b805edcf9e28a50e537dc84f561e1460c7567
+size 19471300