{"id":23174661,"url":"https://github.com/mansurpro/prompt2clip","last_synced_at":"2025-07-28T01:34:30.211Z","repository":{"id":267210886,"uuid":"897675813","full_name":"MansurPro/Prompt2Clip","owner":"MansurPro","description":"Prompt2Clip is a cloud-based application for generating high-quality videos from textual prompts using the Mochi video generation model. This project demonstrates the integration of advanced AI models with scalable cloud infrastructure, enabling the creation of visually compelling video clips directly from descriptive text inputs.","archived":false,"fork":false,"pushed_at":"2025-01-12T19:15:48.000Z","size":229,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-05T00:43:06.846Z","etag":null,"topics":["cloud-based","data-science","dataset","fine-tuning","model","text-to-video","text-to-video-generation","videos","yolo"],"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/MansurPro.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}},"created_at":"2024-12-03T03:24:44.000Z","updated_at":"2025-01-12T19:15:51.000Z","dependencies_parsed_at":"2024-12-09T03:36:59.734Z","dependency_job_id":"b4da5260-a75f-4772-bbd9-06f0113ee00e","html_url":"https://github.com/MansurPro/Prompt2Clip","commit_stats":null,"previous_names":["mansurpro/prompt2clip"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/MansurPro/Prompt2Clip","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MansurPro%2FPrompt2Clip","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MansurPro%2FPrompt2Clip/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MansurPro%2FPrompt2Clip/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MansurPro%2FPrompt2Clip/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MansurPro","download_url":"https://codeload.github.com/MansurPro/Prompt2Clip/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MansurPro%2FPrompt2Clip/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267451093,"owners_count":24089293,"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":"2025-07-27T02:00:11.917Z","response_time":82,"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":["cloud-based","data-science","dataset","fine-tuning","model","text-to-video","text-to-video-generation","videos","yolo"],"created_at":"2024-12-18T05:30:53.037Z","updated_at":"2025-07-28T01:34:30.185Z","avatar_url":"https://github.com/MansurPro.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# 🎥 **Prompt2Clip**\n\nPrompt2Clip generates high-quality videos from text prompts using YOLOv10 models. Designed for efficiency and flexibility, it fine-tunes object detection models on custom datasets and enables real-time inference for a seamless text-to-video experience.\n\n---\n\n## 🚀 **Key Features**\n\n- **Text-to-Video Conversion**: Converts natural language prompts into video clips.  \n- **Custom Dataset Training**: Fine-tunes YOLOv10 models with bird and bee datasets for enhanced detection.  \n- **Real-Time Inference**: Supports single-image and streaming video detection.  \n- **Cloud-Based Workflow**: Uses Google Colab for GPU-accelerated training and processing.  \n- **Customizable Parameters**: Flexible settings for model size, inference steps, and detection thresholds.\n\n---\n\n## 🛠️ **How It Works**\n\nPrompt2Clip combines advanced AI models and custom workflows:\n1. **Dataset Integration**: Downloads datasets from Roboflow for custom object detection tasks.\n2. **Model Training**: Fine-tunes YOLOv10 on labeled datasets for accurate detection.\n3. **Video Generation**: Combines frames generated through detection into cohesive video clips.\n4. **Inference Pipelines**: Enables real-time detection on single images or streaming video.\n\n---\n\n## 📂 **Project Structure**\n\n```plaintext\nPrompt2Clip/\n│\n├── datasets/           # Custom datasets for birds and bees\n├── models/             # Pre-trained and fine-tuned YOLOv10 models\n├── scripts/            # Scripts for training, inference, and video generation\n├── examples/           # Example outputs of text-to-video generation\n└── README.md           # Project documentation\n```\n\n---\n\n## 🖥️ **Usage**\n\n### **1. Clone the Repository**\n\n```bash\ngit clone https://github.com/MansurPro/Prompt2Clip.git\ncd Prompt2Clip\n```\n\n### **2. Set Up the Environment**\n\nRun Prompt2Clip in Google Colab for GPU-accelerated operations. Install the required Python packages:\n\n```bash\npip install -r requirements.txt\n```\n\n### **3. Train the Model**\n\n```bash\npython train.py --dataset datasets/birds --model yolov10m.pt --epochs 10\n```\n\n### **4. Run Inference**\n\n```bash\npython inference.py --image_path path/to/image.jpg --model_path models/yolov10_best.pt\n```\n\n---\n\n## 🎨 **Examples**\n\n| **Prompt**                    | **Generated Video**                |\n|--------------------------------|-------------------------------------|\n| \"A bird flying over a forest\"  | [View](examples/bird_forest.mp4)   |\n| \"A bee hovering near a flower\" | [View](examples/bee_flower.mp4)    |\n\n---\n\n## 📊 **Performance**\n\n- **Efficiency**: Fine-tuned for fast and accurate text-to-video generation.  \n- **Customizability**: Supports flexible detection thresholds and model configurations.  \n- **Scalability**: Leverages GPU resources for high-throughput operations.\n\n---\n\n## 📜 **License**\n\nThis project is licensed under the MIT License. See the `LICENSE` file for details.\n\n---\n\n## 🙌 **Acknowledgments**\n\nPrompt2Clip builds on the following open-source tools and datasets:\n- **YOLOv10** for object detection.\n- **Roboflow** for dataset integration.\n- **Google Colab** for cloud-based GPU acceleration.\n\nThank you to the open-source community for enabling innovative solutions like this!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmansurpro%2Fprompt2clip","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmansurpro%2Fprompt2clip","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmansurpro%2Fprompt2clip/lists"}