Update README.md

README.md

@@ -31,7 +31,7 @@ Here are some "Fakemons" generated by the model: (64x64 Resolution)
 
 ![image](https://cdn-uploads.huggingface.co/production/uploads/68df176c403a7bf9e8ae85a8/pkP0-pWDjxDZkvXrBnJYQ.png)
 
-## 🧠 Overview
+## Overview
 
 TinyPokemonDiffusion is a lightweight DDPM-based generative model trained on Pokémon images.
 
@@ -42,7 +42,7 @@ Despite its small size and CPU-only training, the model learns:
 
 ---
 
-## ⚙️ Specifications
+##  Specifications
 
 | Component        | Value |
 |------------------|------|
@@ -56,7 +56,7 @@ Despite its small size and CPU-only training, the model learns:
 
 ---
 
-## 🧪 Features
+##  Features
 
 - Full DDPM implementation from scratch
 - Custom UNet with attention blocks
@@ -66,7 +66,7 @@ Despite its small size and CPU-only training, the model learns:
 
 ---
 
-## 🖼️ Results
+## Results
 
 The model generates:
 
@@ -81,9 +81,8 @@ Limitations:
 
 ---
 
-## THE INITIAL IDEA WAS A STUDENT U-NET FROM A TEACHER U-NET, BUT THIS WAS DISCONTINUED BECAUSE THE TEACHER WAS INITIALIZATED WITH RANDOM WEIGHTS, THAT WOULD KILL THE STUDENT LEARNING
 
-## 🚀 Usage
+##  Usage
 
 ### Generate images
 
@@ -174,13 +173,13 @@ python generate.py \
   --seed 42
 ```
 
-📁 Output
+ Output
 
 Generated images are saved as a horizontal grid:
 
 outputs/generated.png
 
->> ⚠️ Limitations 
+>>  Limitations 
 
 Unconditional model (no prompts)
 
@@ -188,7 +187,7 @@ Limited dataset diversity
 Early training stage
 No DDIM (yet)
 
->> 🔬 Research Direction
+>>  Research Direction
 
 This project demonstrates that:
 
@@ -200,7 +199,7 @@ Conditional generation (class-based)
 Text-to-image (v2.0)
 DDIM sampling
 Larger model variants
-💡 Motivation
+ Motivation
 
 Most diffusion research focuses on scaling up.
 
@@ -208,16 +207,19 @@ This project explores the opposite direction:
 
 What is the minimum viable diffusion model?
 
-📜 License
+ License
 
 MIT
 
-🙌 Acknowledgments
+ Acknowledgments
 
 Hugging Face datasets
 PyTorch
 The open-source AI community
 
-⭐ If you like this project:
+ If you like this project:
 
-Give it a star and follow the evolution to v2.0(conditional) 🚀
+Give it a star and follow the evolution to v2.0(conditional) 
+
+## Other 
+THE INITIAL IDEA WAS A STUDENT U-NET FROM A TEACHER U-NET, BUT THIS WAS DISCONTINUED BECAUSE THE TEACHER WAS INITIALIZATED WITH RANDOM WEIGHTS, THAT WOULD KILL THE STUDENT LEARNING