{"id":26237500,"url":"https://github.com/codewitheshayoutube/imageembedder_using_deeplearning-1","last_synced_at":"2026-04-21T22:04:41.306Z","repository":{"id":282004448,"uuid":"947159537","full_name":"codewithEshaYoutube/ImageEmbedder_using_deeplearning-1","owner":"codewithEshaYoutube","description":null,"archived":false,"fork":false,"pushed_at":"2025-03-12T08:57:26.000Z","size":0,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-12T09:39:04.631Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/codewithEshaYoutube.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-12T08:48:20.000Z","updated_at":"2025-03-12T08:57:30.000Z","dependencies_parsed_at":"2025-03-12T09:49:05.600Z","dependency_job_id":null,"html_url":"https://github.com/codewithEshaYoutube/ImageEmbedder_using_deeplearning-1","commit_stats":null,"previous_names":["codewitheshayoutube/imageembedder_using_deeplearning-1"],"tags_count":0,"template":false,"template_full_name":"streamlit/blank-app-template","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithEshaYoutube%2FImageEmbedder_using_deeplearning-1","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithEshaYoutube%2FImageEmbedder_using_deeplearning-1/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithEshaYoutube%2FImageEmbedder_using_deeplearning-1/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithEshaYoutube%2FImageEmbedder_using_deeplearning-1/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/codewithEshaYoutube","download_url":"https://codeload.github.com/codewithEshaYoutube/ImageEmbedder_using_deeplearning-1/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243349567,"owners_count":20276622,"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","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":[],"created_at":"2025-03-13T05:28:31.049Z","updated_at":"2025-12-29T22:05:46.053Z","avatar_url":"https://github.com/codewithEshaYoutube.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 📌 ImageEmbedder: AI-Powered Object Embedding\n[![Open in Streamlit by Eesha Tariq](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://image-embedder-using-deeplearning.streamlit.app/)\n\n\n## 🌟 Overview\n**ImageEmbedder** is a Streamlit-based web app that allows users to seamlessly embed objects into images using AI. It utilizes **CLIP (ViT-L/14) from Hugging Face** to intelligently determine the **best placement** for objects based on semantic similarity.\n\n\n## 🛠 Features\n✅ Upload a **background image** and an **object image**\n✅ Uses **CLIP model** to find the **optimal placement** for the object\n✅ Supports **manual adjustments** (X, Y position \u0026 scaling)\n✅ **Seamless blending** using OpenCV \u0026 PIL\n✅ Web-based interface using **Streamlit**\n\n---\n\n## 🚀 Technologies Used\n- **Python 3.x**\n- **Hugging Face Transformers** (CLIP model: `openai/clip-vit-large-patch14`)\n- **OpenCV** (for image processing)\n- **NumPy** (for numerical operations)\n- **PIL (Pillow)** (image manipulation)\n- **Streamlit** (for UI)\n\n---\n\n## 📥 Installation\n\n### 1️⃣ Clone the Repository\n```sh\ngit clone https://github.com/yourusername/ImageEmbedder.git\ncd ImageEmbedder\n```\n\n### 2️⃣ Install Dependencies\n```sh\npip install -r requirements.txt\n```\n\n---\n\n## 🎯 Usage\n\n### 🔹 Run the Streamlit App\n```sh\nstreamlit run app.py\n```\n\n### 🔹 Steps\n1. **Upload a background image**\n2. **Upload an object image (PNG with transparency recommended)**\n3. Click **\"Find Best Placement with CLIP\"**\n4. AI suggests the **best position** based on context\n5. Optionally **adjust manually** \u0026 save the final image\n\n---\n\n## 🔬 How CLIP is Used\n1. **Extracts features** from the background \u0026 object images.\n2. **Computes similarity scores** across different regions.\n3. **Finds the most contextually relevant area** to place the object.\n4. **Blends the object** seamlessly into the background.\n\n---\n\n## 📌 Example Output\n![Example](assets/example_output.jpg)\n\n---\n\n## 📌 Future Enhancements\n🚀 Add **text-based placement** (e.g., \"Place near the tree\")\n🚀 Improve **adaptive scaling** for different image sizes\n🚀 Support **multiple object embeddings**\n\n---\n\n## 📜 License\nThis project is **open-source** under the MIT License.\n\n👨‍💻 Built with ❤️ by **Eesha Tariq** during Research Internship at **University of Sharjah**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodewitheshayoutube%2Fimageembedder_using_deeplearning-1","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodewitheshayoutube%2Fimageembedder_using_deeplearning-1","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodewitheshayoutube%2Fimageembedder_using_deeplearning-1/lists"}