ViralCutter.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# ViralCutter\n",
        "Uma alternativa gratuita ao `opus.pro` e ao `vidyo.ai`"
      ],
      "metadata": {
        "id": "pa36OeArowme"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Suporte em:\n",
        "[![](https://dcbadge.limes.pink/api/server/tAdPHFAbud)](https://discord.gg/tAdPHFAbud)"
      ],
      "metadata": {
        "id": "6Q-ljfsw1unE"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# TODO📝\n",
        "- [x] Release code\n",
        "- [ ] Huggingface SpaceDemo\n",
        "- [x] Two face in the cut\n",
        "- [x] Custom caption and burn\n",
        "- [x] Make the code faster\n",
        "- [ ] More types of framing beyond 9:16"
      ],
      "metadata": {
        "id": "0o3KcBT5wzws"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "e76jiRnjONmj",
        "cellView": "form",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "6e8baa39-5e40-45d7-e247-a70eddbc1a79"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "✅ Instalação V7 Finalizada!\n",
            "- Transformers 4.46.3 (Compatível com Alinhamento): INSTALADO\n",
            "- Torch 2.3.1: ATIVO\n"
          ]
        }
      ],
      "source": [
        "#@title 🛠️ Instalação\n",
        "import os\n",
        "import subprocess\n",
        "import shutil\n",
        "from IPython.display import clear_output\n",
        "\n",
        "# 1. Limpeza TOTAL\n",
        "print(\"🧹 Limpando instalação anterior...\")\n",
        "%cd /content\n",
        "if os.path.exists(\"ViralCutter\"):\n",
        "    shutil.rmtree(\"ViralCutter\")\n",
        "\n",
        "!git clone -b dev https://github.com/RafaelGodoyEbert/ViralCutter.git\n",
        "%cd /content/ViralCutter\n",
        "\n",
        "print(\"⏳ Instalando gerenciador UV e drivers do sistema...\")\n",
        "\n",
        "# 2. Instalar UV e Drivers Linux\n",
        "subprocess.run(['pip', 'install', 'uv'], check=True)\n",
        "subprocess.run('sudo apt update -y && sudo apt install -y libcudnn8 ffmpeg xvfb', shell=True, check=True)\n",
        "\n",
        "# 3. Criar Ambiente Virtual\n",
        "print(\"⏳ Criando ambiente virtual...\")\n",
        "subprocess.run(['uv', 'venv', '.venv'], check=True)\n",
        "\n",
        "# 4. INSTALAÇÃO DAS DEPENDÊNCIAS\n",
        "print(\"⏳ Instalando Bibliotecas...\")\n",
        "\n",
        "# Passo A: WhisperX e Requisitos Básicos (Deixe instalar o que quiserem)\n",
        "cmds_fase_1 = [\n",
        "    \"uv pip install --python .venv git+https://github.com/m-bain/whisperx.git\",\n",
        "    \"uv pip install --python .venv -r requirements.txt\",\n",
        "    \"uv pip install --python .venv yt-dlp pytubefix\",\n",
        "    \"uv pip install yt_dlp\"\n",
        "]\n",
        "\n",
        "for cmd in cmds_fase_1:\n",
        "    subprocess.run(cmd, shell=True, check=True)\n",
        "\n",
        "# Passo B: CORREÇÃO DE ALINHAMENTO E GEMINI\n",
        "# - google-generativeai: Para o Gemini funcionar\n",
        "# - pandas: Para separar palavras\n",
        "# - transformers==4.46.3: VERSÃO CRÍTICA. Versões mais novas exigem Torch 2.6 e quebram o alinhamento.\n",
        "# - accelerate: Ajuda no carregamento do modelo\n",
        "print(\"🔨 Aplicando downgrade estratégico no Transformers...\")\n",
        "extra_libs = [\n",
        "    \"uv pip install --python .venv google-generativeai\",\n",
        "    \"uv pip install --python .venv pandas\",\n",
        "    \"uv pip install --python .venv onnxruntime-gpu\",\n",
        "    \"uv pip install --python .venv transformers==4.46.3 accelerate>=0.26.0\"\n",
        "]\n",
        "\n",
        "for cmd in extra_libs:\n",
        "    subprocess.run(cmd, shell=True, check=True)\n",
        "\n",
        "# Passo C: O MARTELO FINAL (Torch 2.3.1 Estável)\n",
        "# Reinstalamos por último para garantir que nada atualizou ele sem querer\n",
        "print(\"🔨 Forçando versão estável do Torch (2.3.1)...\")\n",
        "cmd_fix_torch = (\n",
        "    \"uv pip install --python .venv \"\n",
        "    \"torch==2.3.1+cu121 torchvision==0.18.1+cu121 torchaudio==2.3.1+cu121 \"\n",
        "    \"--index-url https://download.pytorch.org/whl/cu121\"\n",
        ")\n",
        "subprocess.run(cmd_fix_torch, shell=True, check=True)\n",
        "\n",
        "# Passo D: Trava do Numpy\n",
        "print(\"🔨 Travando Numpy...\")\n",
        "subprocess.run(\"uv pip install --python .venv 'numpy<2.0' setuptools==69.5.1\", shell=True, check=True)\n",
        "\n",
        "# Passo E: Correção de Visão Computacional (CRÍTICO)\n",
        "print(\"🔨 Corrigindo InsightFace e MediaPipe...\")\n",
        "\n",
        "# 1. Garante que o InsightFace tenha o motor necessário (evita que ele falhe)\n",
        "subprocess.run(\"uv pip install --python .venv insightface onnxruntime-gpu\", shell=True, check=True)\n",
        "\n",
        "# 2. Limpeza Radical e Reinstalação do MediaPipe\n",
        "# Remove versões quebradas\n",
        "subprocess.run(\"uv pip uninstall --python .venv mediapipe protobuf flatbuffers\", shell=True)\n",
        "\n",
        "# 3. Instala versão FLEXÍVEL respeitando limites críticos\n",
        "# mediapipe>=0.10.0: Pega a versão mais recente compatível com Py3.12\n",
        "# protobuf>=3.20,<5.0: Garante compatibilidade sem quebrar o sistema antigo\n",
        "subprocess.run(\"uv pip install --python .venv 'mediapipe>=0.10.0' 'protobuf>=3.20,<5.0' 'flatbuffers>=2.0'\", shell=True, check=True)\n",
        "\n",
        "# 5. Configurar Monitor\n",
        "os.system('Xvfb :1 -screen 0 2560x1440x8 &')\n",
        "os.environ['DISPLAY'] = ':1.0'\n",
        "\n",
        "clear_output()\n",
        "print(\"✅ Instalação V7 Finalizada!\")\n",
        "print(\"- Transformers 4.46.3 (Compatível com Alinhamento): INSTALADO\")\n",
        "print(\"- Torch 2.3.1: ATIVO\")"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#@title 🚀 Configuração e Execução\n",
        "import os\n",
        "\n",
        "%cd /content/ViralCutter\n",
        "\n",
        "# 1. Configura o \"Display\" falso (para evitar erros de interface gráfica)\n",
        "os.system('Xvfb :1 -screen 0 2560x1440x8 &')\n",
        "os.environ['DISPLAY'] = ':1.0'\n",
        "\n",
        "# 2. CORREÇÃO DO ERRO ATUAL:\n",
        "# Forçamos o Matplotlib a usar o backend 'Agg' (modo sem cabeça/headless)\n",
        "# Isso ignora o 'module://matplotlib_inline.backend_inline' que o Colab força e quebra o script.\n",
        "os.environ['MPLBACKEND'] = 'Agg'\n",
        "\n",
        "print(\"🚀 Iniciando ViralCutter usando o ambiente virtual...\")\n",
        "print(\"⚠️ Ignore os avisos de 'UserWarning', aguarde o link public URL.\")\n",
        "\n",
        "# Executa usando o Python do ambiente virtual\n",
        "!/content/ViralCutter/.venv/bin/python webui/app.py --colab"
      ],
      "metadata": {
        "id": "DNn8ZKJdD5XG",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "fd4689bd-f036-42de-fc7e-67854af40d81"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content/ViralCutter\n",
            "🚀 Iniciando ViralCutter usando o ambiente virtual...\n",
            "⚠️ Ignore os avisos de 'UserWarning', aguarde o link public URL.\n",
            "/content/ViralCutter/webui/app.py:204: UserWarning: The parameters have been moved from the Blocks constructor to the launch() method in Gradio 6.0: theme, css. Please pass these parameters to launch() instead.\n",
            "  with gr.Blocks(title=i18n(\"ViralCutter WebUI\"), theme=gr.themes.Default(primary_hue=\"blue\", neutral_hue=\"slate\"), css=css) as demo:\n",
            "Running in Colab mode. Generating public link...\n",
            "* Running on local URL:  http://127.0.0.1:7860\n",
            "* Running on public URL: https://7f3b04ec670707105b.gradio.live\n",
            "\n",
            "This share link expires in 1 week. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nEIsMZLwJ5kD"
      },
      "source": [
        "#Créditos\n",
        "\n",
        "Inspirado no [reels clips automator](https://github.com/eddieoz/reels-clips-automator) e no [YoutubeVideoToAIPoweredShorts](https://github.com/Fitsbit/YoutubeVideoToAIPoweredShorts)<br>\n",
        "\n",
        "---\n",
        "![Rafa.png](https://i.imgur.com/cGknQpU.png;base64)\n",
        "\n",
        "Desenvolvido por **Rafa.Godoy**<br>\n",
        "[ ![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white) ](https://github.com/rafaelGodoyEbert)<br>\n",
        "[ ![X](https://img.shields.io/twitter/url?url=https%3A%2F%2Ftwitter.com%2FGodoyEbert) ](https://twitter.com/GodoyEbert)<br>\n",
        "[Instagram](https://www.instagram.com/rafael.godoy.ebert/)<br>\n",
        "[ ![](https://dcbadge.vercel.app/api/server/aihubbrasil) ](https://discord.gg/aihubbrasil)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "`0.1v Alpha`<br>\n",
        "\n",
        "Apenas uma alternativa gratuita ao `opus.pro` e ao `vidyo.ai`<br>\n"
      ],
      "metadata": {
        "id": "tpLJmPqGT5_u"
      }
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}