https://github.com/sumdiboii/advanced-diffusion-models-for-image-generation-public

FreeCrafter is a responsive web app for generating images with six free AI models, featuring real-time analytics and smart prompt suggestions. Developed for our Business Intelligence and Computer Vision course under Dr. Ganesh Kadam by a team of three.
https://github.com/sumdiboii/advanced-diffusion-models-for-image-generation-public

ai-image-generation business-intelligence-analytics computer-vision flux-models huggingface-models reactjs real-time-metrics smart-prompt-recommendations stable-diffusion

Last synced: 19 days ago
JSON representation

FreeCrafter is a responsive web app for generating images with six free AI models, featuring real-time analytics and smart prompt suggestions. Developed for our Business Intelligence and Computer Vision course under Dr. Ganesh Kadam by a team of three.

• Host: GitHub
• URL: https://github.com/sumdiboii/advanced-diffusion-models-for-image-generation-public
• Owner: Sumdiboii
• Created: 2025-08-14T20:28:38.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2025-08-16T10:17:00.000Z (11 months ago)
• Last Synced: 2025-08-16T12:52:16.053Z (11 months ago)
• Topics: ai-image-generation, business-intelligence-analytics, computer-vision, flux-models, huggingface-models, reactjs, real-time-metrics, smart-prompt-recommendations, stable-diffusion
• Homepage: https://advanced-diffusion-models-for-image.vercel.app/
• Size: 1.54 MB
• Stars: 1
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          



  





  





🎨 FreeCrafter AI Image Generator 🤖

Team: Sumedh Pimplikar, Nikhil Pattewar & Soham Pawar

Guided by: Dr. Ganesh Kadam







  

  

  

  

  



---

## 📖 Overview

**FreeCrafter** is a modern, responsive web application for generating images using **six free, state-of-the-art AI models**.  Built with **React**, styled using **Tailwind CSS** and **custom/vanilla CSS**, it offers **real-time analytics, smart prompt recommendations**, and a **user-friendly interface**.  All image generations and analytics are handled on the **frontend** using **Hugging Face Inference API** endpoints.

---



 

  




  

  


  

  


  

  


  

  


  

  


  



---

## 🚀 Features

### 🎨 AI Model Selection

- Choose from 6 free models:  

  - Stable Diffusion XL Base 1.0  

  - Stable Diffusion 2.1  

  - Stable Diffusion 1.5  

  - Stable Diffusion 3 Medium  

  - FLUX.1-dev  

  - FLUX.1-schnell  

- Each model displays **parameters, strengths, weaknesses, and best use cases**.

 


### 🖼️ Image Generation

- Input prompts or optionally upload a reference image.  

- Generate images via the selected model using **Hugging Face API**.  

- Download or open generated images in a new window.

 


### 📚 History

- Stores up to **50 previous generations** locally.  

- View **thumbnails, prompts, model used, and generation date**.  

- Reload previous generations or clear history easily.

 


### 📊 Analytics Dashboard

- Real-time metrics: total generations, success rate, average generation time.  

- Model usage distribution chart.  

- Model performance comparison table including:  

  - Usage count & percentage  

  - Average prompt length  

  - Recent usage (last 24h)  

  - Speed (avg. generation time)  

  - Last image thumbnail  

  - Cost efficiency (all models free)

 


### 💡 Smart Recommendations

- Prompt suggestions based on **selected model, style enhancements, and popular keywords**.

 


 

### 🌙 Responsive UI

- Desktop & mobile navigation  

- Light/Dark theme toggle  

- Clean, modern design combining **Tailwind CSS and custom/vanilla CSS**  

 


 

---

 


 

## ⚙️ Technical Details

- **Frontend:** React 18  

- **Styling:** Tailwind CSS + custom/vanilla CSS for specific overrides  

- **API Integration:** Hugging Face Inference endpoints  

- **State Management:** React hooks, `localStorage` for history & analytics  

- **No Backend Required:** All analytics and history are calculated client-side  

- **Accessibility:** ARIA labels, keyboard navigation, responsive design  

 


 

---

 


 

## 🛠️ How It Works

1. **Select a Model:** Browse the models guide and pick the best fit.  

2. **Enter a Prompt:** Describe your desired image. Optionally upload a reference image.  

3. **Generate & View:** Prompt is sent to the API endpoint and the generated image is displayed.  

4. **Analyze & Compare:** Use analytics to compare performance, trends, and get smart recommendations.  

5. **History:** Access previous generations, reload prompts, and manage history.

 


 

---

 


 

## 🧩 Models Supported

- Stable Diffusion XL Base 1.0  

- Stable Diffusion 2.1  

- Stable Diffusion 1.5  

- Stable Diffusion 3 Medium  

- FLUX.1-dev  

- FLUX.1-schnell

 


 

---

 


 

## 📈 Analytics & Metrics

- All metrics are calculated in **real time** from local history.  

- No hardcoded or random values.  

- Metrics include: usage, prompt length, recent usage, speed, and last image thumbnail.

 


 

---

 


 

## 💡 Smart Recommendations

- Model-specific tips  

- Style enhancements  

- Popular keywords from successful generations  

 


 

---

 


 

## 📬 Contact

  

    Platform

    Link

  

  

    📧 Email

    sumedh.pimplikar22@pccoepune.org

  

  

    💼 LinkedIn

    linkedin.com/in/sumedh-pimplikar

  

  

    💻 GitHub

     


    github.com/Sumdiboii