{"id":28799725,"url":"https://github.com/thekartikeyamishra/lipsyncblinking-ai","last_synced_at":"2026-04-16T19:40:49.913Z","repository":{"id":295141978,"uuid":"989302811","full_name":"thekartikeyamishra/LipsyncBlinking-AI","owner":"thekartikeyamishra","description":"A Google Colab tool for creating lipsync and blinking animations from a still image and audio. Uses the SadTalker AI model. Features a user-friendly UI for easy input and video generation. Perfect for bringing characters to life!","archived":false,"fork":false,"pushed_at":"2025-05-23T21:05:54.000Z","size":58,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-22T15:46:24.514Z","etag":null,"topics":["ai","ffmpeg","ipywidgets","jyputer-notebook","machine-learning","python","sadtalker","yt-dlp"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/thekartikeyamishra.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-23T20:52:11.000Z","updated_at":"2025-05-23T21:07:14.000Z","dependencies_parsed_at":"2025-05-23T21:36:48.974Z","dependency_job_id":"72edcc8c-612a-4e1f-b975-75badad42d48","html_url":"https://github.com/thekartikeyamishra/LipsyncBlinking-AI","commit_stats":null,"previous_names":["thekartikeyamishra/lipsyncblinking-ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/thekartikeyamishra/LipsyncBlinking-AI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thekartikeyamishra%2FLipsyncBlinking-AI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thekartikeyamishra%2FLipsyncBlinking-AI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thekartikeyamishra%2FLipsyncBlinking-AI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thekartikeyamishra%2FLipsyncBlinking-AI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thekartikeyamishra","download_url":"https://codeload.github.com/thekartikeyamishra/LipsyncBlinking-AI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thekartikeyamishra%2FLipsyncBlinking-AI/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269828171,"owners_count":24481667,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-11T02:00:10.019Z","response_time":75,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","ffmpeg","ipywidgets","jyputer-notebook","machine-learning","python","sadtalker","yt-dlp"],"created_at":"2025-06-18T07:00:30.128Z","updated_at":"2026-04-16T19:40:49.874Z","avatar_url":"https://github.com/thekartikeyamishra.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🎙️ Interactive Lipsync \u0026 Blinking Animator (LipsyncBlinking-AI) 🖼️ \nA Google Colab tool for creating lipsync and blinking animations from a still image and audio. Uses the SadTalker AI model. Features a user-friendly UI for easy input and video generation. Perfect for bringing characters to life!\n\n\nBring your characters to life! This Google Colab notebook provides a simple, interactive interface to generate talking head animations with realistic lip synchronization and natural eye blinking. It leverages the powerful pre-trained **SadTalker AI model**.\n\n**No complex setup or model training required!** Just upload your image, provide audio, and let the AI do the magic.\n\n## ✨ UI Overview\n\nThe tool provides a clean interface to manage your inputs and generate animations:\n\n*(Image: `ui_overview.PNG` provided by user)*\n![Main UI Screenshot](assets/ui_overview.png)\n*Caption: Main interface for uploading your character image, providing audio (via YouTube URL or file upload), selecting face enhancement options, and generating the animation.*\n\n## 🌟 Features\n\n* **User-Friendly UI:** Simple controls built with `ipywidgets` directly in Google Colab.\n* **Still Image Input:** Upload any character's portrait or image.\n* **Flexible Audio Input:**\n    * Paste a YouTube URL (audio will be extracted automatically).\n    * Upload your own audio file (e.g., `.wav`, `.mp3`).\n* **High-Quality Animation:** Powered by SadTalker for realistic lipsync and blinking.\n* **Face Enhancement:** Optional face enhancement using GFPGAN or RestoreFormer.\n* **Still Mode:** Option to reduce head movement, ideal for portrait-style animations.\n* **Instant Preview:** View the generated video directly in the notebook.\n* **Easy Download:** Download your animated video.\n\n## 🚀 How to Use\n\n1.  **Open in Colab:**\n    * Click the \"Open in Colab\" badge above.\n    * Or, go to [Google Colab](https://colab.research.google.com/) and upload the `.ipynb` notebook file from this repository.\n2.  **Run Setup Cell:**\n    * Execute the first code cell (labeled \"**Step 1: Setup Environment**\").\n    * This will clone the SadTalker repository, install all necessary dependencies, and download the pre-trained AI models.\n    * **This step might take a few minutes**, especially on the first run. Please be patient! You'll see a \"✅ Setup Complete!\" message when it's done.\n    * Ensure your Colab runtime has a **GPU enabled** for faster processing (`Runtime` \u003e `Change runtime type` \u003e `Hardware accelerator` \u003e `GPU`).\n3.  **Upload Inputs \u0026 Configure (Step 2 UI Cell - See UI Overview Image Above):**\n    * Once setup is complete, run the second code cell (labeled \"**Step 2: Upload Your Character \u0026 Audio, then Animate!**\"). This will display the interactive UI.\n    * **1. Upload Character Image:** Click the \"Upload Character Image\" button and select your desired image file (e.g., JPG, PNG). A preview will appear.\n    * **2. Provide Audio Source:**\n        * Choose \"YouTube URL\" and paste the link.\n        * OR choose \"Upload Audio File\" and upload your `.wav` or `.mp3` file. Audio controls will appear if the file is valid.\n    * **3. Select Face Enhancer:** Choose an option like 'gfpgan' for better facial clarity in the output, or 'None'.\n    * **Enable Still Mode (Optional):** Check this box if you want minimal head movement (recommended for static portraits).\n4.  **Generate Animation:**\n    * Click the \"🎬 **Generate Animation!**\" button.\n    * The \"Status \u0026 Logs\" section will show progress updates. This process can take a few minutes depending on the audio length and selected options.\n5.  **View \u0026 Download:**\n    * Once complete, the generated video will appear in the \"Output Video\" section.\n    * A download link for the video will also be provided.\n\n## 🔧 Behind the Scenes\n\n* **SadTalker:** This project uses the [SadTalker (CVPR 2023)](https://github.com/OpenTalker/SadTalker) model, which synthesizes a talking head video from a single image and an audio track. It excels at producing natural facial expressions, including blinks and head movements that synchronize with the audio.\n* **`yt-dlp`:** Used for extracting audio from YouTube URLs.\n* **`ffmpeg`:** For audio processing.\n* **`ipywidgets`:** For creating the interactive UI components in Colab.\n\n## 🤝 Contributing\n\nWhile this is a self-contained Colab tool, suggestions for improving the UI, adding more SadTalker parameter controls, or enhancing error handling are welcome!\n1.  Fork the repository.\n2.  Create your feature branch (`git checkout -b feature/AmazingFeature`).\n3.  Commit your changes (`git commit -m 'Add some AmazingFeature'`).\n4.  Push to the branch (`git push origin feature/AmazingFeature`).\n5.  Open a Pull Request.\n\n## 📜 License\n\nThis project is licensed under the MIT License - see the `LICENSE.md` file for details (you'll need to add one). The underlying SadTalker model has its own license, which you should also respect.\n\n## 🙏 Acknowledgements\n\n* The authors of [SadTalker](https://sadtalker.github.io/) for their incredible work and open-sourcing their model.\n* The developers of the various Python libraries used in this project.\n\n---\n\nEnjoy creating your animations!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthekartikeyamishra%2Flipsyncblinking-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthekartikeyamishra%2Flipsyncblinking-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthekartikeyamishra%2Flipsyncblinking-ai/lists"}