{"id":32867170,"url":"https://github.com/sourav-x-3202/aiman","last_synced_at":"2026-05-07T03:33:38.828Z","repository":{"id":323229218,"uuid":"1092401298","full_name":"Sourav-x-3202/aiman","owner":"Sourav-x-3202","description":"Offline Cinematic AI — Text → Motivation → Image → Voice. which uses Local LLM (Ollama φ3) + Stable Diffusion + TTS → motivational cinematic output. Runs 100% locally.","archived":false,"fork":false,"pushed_at":"2025-11-08T21:37:41.000Z","size":299,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-11-08T23:27:30.779Z","etag":null,"topics":["ai","generative-ai","generative-ai-projects","motivational-ai","offline-ai","ollama","phi3","stable-diffusion","streamlit","text-to-speech-python3"],"latest_commit_sha":null,"homepage":"","language":"Python","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/Sourav-x-3202.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-08T15:05:43.000Z","updated_at":"2025-11-08T21:44:17.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Sourav-x-3202/aiman","commit_stats":null,"previous_names":["sourav-x-3202/aiman"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Sourav-x-3202/aiman","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sourav-x-3202%2Faiman","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sourav-x-3202%2Faiman/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sourav-x-3202%2Faiman/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sourav-x-3202%2Faiman/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Sourav-x-3202","download_url":"https://codeload.github.com/Sourav-x-3202/aiman/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sourav-x-3202%2Faiman/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":283464470,"owners_count":26840238,"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":"2025-11-09T02:00:05.828Z","response_time":62,"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","generative-ai","generative-ai-projects","motivational-ai","offline-ai","ollama","phi3","stable-diffusion","streamlit","text-to-speech-python3"],"created_at":"2025-11-09T06:00:43.665Z","updated_at":"2026-05-07T03:33:38.821Z","avatar_url":"https://github.com/Sourav-x-3202.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003c!--  Project Banner --\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"100%\" src=\"https://github.com/user-attachments/assets/a30a8186-5429-4ce2-86bf-38a5cc1f0310\" alt=\"AIMAN Cinematic Banner\"/\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003e AIMAN — Cinematic Motivational AI\u003c/h1\u003e\n\u003cp align=\"center\"\u003e\u003ci\u003e“Type your pain. Receive motivation.”\u003c/i\u003e\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/Sourav-x-3202/aiman/stargazers\"\u003e\n    \u003cimg src=\"https://img.shields.io/github/stars/Sourav-x-3202/aiman?style=flat-square\u0026logo=github\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://github.com/Sourav-x-3202/aiman/issues\"\u003e\n    \u003cimg src=\"https://img.shields.io/github/issues/Sourav-x-3202/aiman?style=flat-square\" /\u003e\n  \u003c/a\u003e\n  \u003cimg src=\"https://img.shields.io/badge/AI-Offline%20%7C%20Private-blue?style=flat-square\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Made%20with-Streamlit-FF4B4B?logo=streamlit\u0026style=flat-square\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/License-MIT-green?style=flat-square\" /\u003e\n    \u003ca href=\"https://codespaces.new/Sourav-x-3202/aiman\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Run%20in-Codespaces-purple?style=flat-square\u0026logo=github\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n\n##  Table of Contents\n- [ Demo](#demo)\n- [ Screenshots](#screenshots)\n- [ Overview](#overview)\n- [ How It Works](#how-it-works)\n- [ Key Features](#key-features---what-aiman-does)\n- [ Tech Stack](#tech-stack)\n- [ Installation](#installation)\n- [ Usage](#usage)\n- [ Folder Structure](#project-structure)\n- [ Developer Notes](#developer-notes)\n- [ Roadmap](#roadmap)\n- [ Contribute](#contribute)\n- [ Cinematic Design Philosophy](#cinematic-design-philosophy)\n- [ License](#license)\n\n---\n\n\n##  Demo\n\n| User Input | AI Generated Image + Cinematic Quote | AI Voice Output |\n|------------|-------------------------------------|------------------|\n| _\"I lost my job as a graphic designer due to AI and now I'm nothing.\"_ | \u003cimg src=\"https://github.com/user-attachments/assets/018ac3fb-cf66-4e2d-8f51-15ee849b50b1\" width=\"450\"\u003e |  [🎧 Play Voice](https://github.com/user-attachments/files/23434462/82b4b61cfdaaf5500b0b0f4c8f04549c3d30cfb9d4f3bf286b7fb134.wav) |\n\n\u003e Your message → AI motivation → Cinematic image → Spoken in voice.\n\n---\n\n## Screenshots\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"750\" src=\"https://github.com/user-attachments/assets/83f821f3-fb96-436b-9b6d-cea5a4c75cea\" /\u003e\n  \u003cimg width=\"750\" src=\"https://github.com/user-attachments/assets/f4aaad3a-3bcc-4b03-becb-4c1898988486\" /\u003e\n\u003c/p\u003e\n\n---\n\n##  Overview\n\n**AIMAN** is a premium **offline cinematic motivational AI**.\n\nYou tell it what you're feeling — stress, failure, heartbreak —  \nand it transforms your message into:\n\n1. A motivational quote (generated by Local LLM — **Ollama phi3:mini**)\n2. A cinematic portrait image (**Stable Diffusion v1.5**)\n3. A deep, masculine **AI voice-over** (pyttsx3)\n\n\u003e Everything happens **locally**.  \n\u003e No internet. No APIs. No tracking.  \n\u003e Your emotions stay yours.\n\n---\n\n##  How It Works\n\n```mermaid\nflowchart LR\n    A[\"User types emotional message\"] --\u003e B[\"Ollama (phi3-mini) generates motivation\"]\n    B --\u003e C[\"Stable Diffusion generates cinematic portrait\"]\n    C --\u003e D[\"pyttsx3 turns quote into deep voice\"]\n    D --\u003e E[\"Outputs: Image + Quote + Voice\"]\n```\n---\n\n##  Key Features - What AIMAN Does\n\n| Feature | Description |\n|---------|-------------|\n|  Understands your emotions | Converts your message into motivational text using `phi3:mini` via **Ollama** |\n|  Generates art | Creates cinematic portraits with **Stable Diffusion** |\n|  Speaks to you | Deep voice using `pyttsx3` (offline) |\n|  100% Local | No internet. No API keys. Privacy-first. |\n|  Beautiful UI | Built in **Streamlit**, just click and use. |\n\n---\n##  Tech Stack\n\n| Area | Tech |\n|------|------|\n| Web UI | Streamlit |\n| LLM Text Generation | Ollama (`phi3:mini`) |\n| Image Generation | Hugging Face Diffusers + Stable Diffusion |\n| Voice / Speech | pyttsx3 (Offline TTS) |\n| Utility | Pillow, Requests, Accelerate |\n\n---\n##  Installation\n### 1. Clone Repo\n\n```bash\ngit clone https://github.com/Sourav-x-3202/aiman.git\ncd aiman\n```\n\n### 2. Create virtual environment\n\n```bash\npython -m venv venv\nvenv\\Scripts\\activate   # Windows\n# or\nsource venv/bin/activate  # Mac/Linux\n```\n\n### 3. Install requirements\n\n```bash\npip install -r requirements.txt\n```\n\n### 4. Start Ollama (Local LLM)\n\n```bash\nollama serve\nollama pull phi3:mini\n```\n\n### 5. Run the app\n\n```bash\nstreamlit run app.py\n```\n---\n\n\u003cdetails\u003e\n\u003csummary\u003e⚠️ Troubleshooting\u003c/summary\u003e\n\n### ❌ `ollama: command not found`\nInstall Ollama from: https://ollama.com/download  \nThen restart your terminal.\n\n---\n\n### ❌ Model not found / Ollama shows no output\nRun this manually once:\n\n```bash\nollama pull phi3:mini\n```\n### ❌ GPU not detected (slow performance)\nAIMAN will automatically switch to CPU mode.\nNo action needed.\n\n### ❌ Text-to-speech not working (no voice)\nOn Windows:\n1. Open Control Panel\n2. Go to: `Speech Recognition → Text to Speech`\n3. Select a male voice (`Guy / David / Microsoft`)\n\n### ❌ `pip install -r requirements.txt` fails\nUpgrade pip first:\n```bash\npython -m pip install --upgrade pip\n```\nIf something still fails, install each dependency manually:\n```bash\npip install streamlit diffusers pillow pyttsx3 accelerate\n```\n### Still stuck?\n\nCreate an issue here:\n https://github.com/Sourav-x-3202/aiman/issues\n\n\u003c/details\u003e\n\n\n---\n\n##  Usage\n\n1. Open Streamlit UI\n2. Enter your pain/frustration/goal\n3. Click Generate Motivation\n4. AIMAN creates:\n   - Voice narration\n   - Motivational message\n   - Cinematic image\n\n     \n### Example (AI Motivation Generation)\n\n```bash\ntext = \"I feel lost and tired of failing.\"\n```\n   \n---\n\n\n\n\n## Project Structure\n\n```bash\naiman/\n│\n├── app.py                   # Streamlit UI\n├── generate_text.py         # AI motivational message generation\n├── motivational_image.py    # Stable Diffusion cinematic image generation\n├── text_to_speech.py        # Voice synthesis\n├── requirements.txt         \n├── README.md\n├── assets/\n│   └── fonts/               # Dancing Script font for overlay text\n└── outputs/                 # Generated images + voice (auto-created)\n\n```\n\n##  Developer Notes\n\n###  Quick Summary \n- Local LLM via **Ollama (phi3:mini)** → Generates motivational text  \n- **Stable Diffusion v1.5** → Creates cinematic portraits  \n- **Pillow + custom font** → Text overlay on image  \n- **pyttsx3 (offline TTS)** → Deep masculine voice  \n- Auto GPU/CPU fallback based on hardware  \n- Outputs timestamp-named files inside `/outputs/`  \n- No API keys, no cloud — 100% private  \n\n---\n\n\u003cdetails\u003e\u003csummary\u003eClick to expand — Full Detailed Developer Notes\u003c/summary\u003e\n\n###  Motivation Engine (Local LLM)\n\n- Uses `phi3:mini` LLM inside Ollama\n- Fully offline — no API calls or internet dependency\n- Custom prompting to maintain:\n  - Cinematic tone (Godfather vibes)\n  - Masculine mentorship voice\n- Ensures messages are:\n  - Short\n  - Powerful\n  - Emotionally supportive  \n- Supports streaming so UI remains responsive\n\n---\n\n###  Stable Diffusion (Cinematic Portrait Generation)\n\n- Model: `runwayml/stable-diffusion-v1-5`\n- Uses `torch.float16` on GPU and `torch.float32` on CPU\n- Image generation pipeline:\n  - Text prompt → latent diffusion → decoding\n- Applies cinematic prompt style:\n  \u003e warm golden light • dramatic shadows • film look\n- Automatically saves images in:\n`outputs/`\n\n---\n\n###  Typography Engine (Quote Overlay)\n\n- Uses Pillow (`ImageDraw` + `ImageFont`)\n- Auto-resizes text to fit image\n- Intelligent line wrapping (prevents broken words)\n- Adds soft drop shadow behind text\n- Uses *Dancing Script Bold* font for elegance  \n(fallback to Arial if font missing)\n\n---\n\n###  Text-to-Speech (Voice Generation)\n\n- `pyttsx3` runs **offline** — no internet requirement\n- Looks for male voice preferences:\n- David\n- Male\n- Guy\n- Parameters tuned for cinematic delivery:\n- Speed: `rate = 145`\n- Volume: `1.0`\n\n---\n\n###  UI Layer (Streamlit App)\n\n- Real-time updates without page reload\n- Sections:\n- Input text\n- Generated quote\n- Generated image\n- Play audio button\n\n---\n\n###  System Behavior\n\n- Timestamp filenames:\n```\noutputs/\n├── ai_image_2025-01-31_211023.png\n├── ai_voice_2025-01-31_211023.wav\n```\n- No overwrites — every output is preserved\n- `.gitignore` ensures:\n- No output files pushed to GitHub\n- No `.wav`, `.png`, `.mp3` leak\n\n---\n\n###  Error Handling \u0026 Fallback Logic\n\n| Situation | AIMAN Response |\n|----------|----------------|\n| Ollama not running | `\" AIMAN is offline\"` |\n| Quote generation failed | Uses backup motivational quote |\n| Font not found | Uses system default font |\n| GPU not detected | Automatic CPU mode |\n\n---\n\n### 🛠 Extensibility (Future)\n\n- Export video reel (portrait + quote + voice)\n- Use user's face as the cinematic output\n- Add background music under voice narration\n\n\u003c/details\u003e\n\n---\n\n##  Roadmap\n\n- Export video (image + voice) — like a motivational reel\n- Add protagonists (your face → AI portrait)\n- Voice emotion control (dominant, calm, intense)\n---\n\n## Contribute\n\nPRs and feature requests are welcome.\n\n- If you like this project, star the repo to support it:\n- https://github.com/Sourav-x-3202/aiman\n\n---\n## Cinematic Design Philosophy\n\n\u003e “Emotion deserves presentation.”\n\u003e \nLike a motivational movie scene — every output should feel *powerful and personal*.\n---\n\n## Author\n\nDeveloped by Sourav Sharma\nIf you like this project, please  star the repo — it motivates the developer \n https://github.com/Sourav-x-3202/aiman\n\n---\n\n## License\n\nMIT License — free to use, modify, and distribute.\n\n\u003cp align=\"center\"\u003e\u003cb\u003eAIMAN\u003c/b\u003e\u003cbr\u003e\u003ci\u003e“Pain is input. Growth is output. AIMAN is the bridge.”\u003c/i\u003e\u003c/p\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsourav-x-3202%2Faiman","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsourav-x-3202%2Faiman","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsourav-x-3202%2Faiman/lists"}