Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 license: creativeml-openrail-m
 base_model: runwayml/stable-diffusion-v1-5
-library_name: transformers.js
+library_name: onnx
 tags:
 - stable-diffusion
 - text-to-image
@@ -9,7 +9,6 @@ tags:
 - webgpu
 - browser-ai
 - onnx
-- transformers.js
 - zhare-ai
 - client-side
 - privacy-preserving
@@ -58,7 +57,6 @@ model-index:
   
 ![License](https://img.shields.io/badge/License-CreativeML_OpenRAIL--M-blue.svg)
 ![WebGPU](https://img.shields.io/badge/WebGPU-Ready-green)
-![Transformers.js](https://img.shields.io/badge/Transformers.js-Compatible-orange)
 ![Privacy](https://img.shields.io/badge/Privacy-First-purple)
 ![Production](https://img.shields.io/badge/Production-Ready-brightgreen)
 
@@ -80,7 +78,6 @@ This is a browser-optimized implementation of Stable Diffusion v1.5, specificall
 - 🔒 **Privacy-First**: All processing happens locally, protecting user prompts and generated content
 - 📱 **Cross-Platform**: Compatible with desktop and mobile browsers
 - 🛠️ **Production-Ready**: Optimized for real-world web applications
-- 🚀 **Transformers.js Compatible**: Direct integration with Hugging Face Transformers.js
 
 ## 🚀 Quick Start
 
@@ -92,57 +89,6 @@ git lfs install
 git clone https://huggingface.co/Zhare-AI/sd-1-5-webgpu
 ```
 
-### Usage with Transformers.js
-
-```javascript
-import { pipeline } from '@huggingface/transformers';
-
-// Initialize the pipeline
-const generator = await pipeline(
-  'text-to-image',
-  'Zhare-AI/sd-1-5-webgpu',
-  {
-    device: 'webgpu',
-    dtype: 'fp16'
-  }
-);
-
-// Generate an image
-const result = await generator(
-  'A majestic mountain landscape at sunrise, digital art',
-  {
-    num_inference_steps: 20,
-    guidance_scale: 7.5,
-    height: 512,
-    width: 512
-  }
-);
-
-// Display the result
-document.getElementById('output').src = result.images[0];
-```
-
-### Advanced Configuration
-
-```javascript
-// Custom generation parameters
-const advancedOptions = {
-  prompt: "A futuristic city with flying cars, neon lights, cyberpunk style",
-  negative_prompt: "blurry, low quality, distorted, ugly, deformed",
-  num_inference_steps: 25,
-  guidance_scale: 8.0,
-  height: 512,
-  width: 512,
-  seed: 12345,  // For reproducible results
-  
-  // Memory optimization for lower-end devices
-  enable_attention_slicing: true,
-  enable_cpu_offload: false
-};
-
-const image = await generator(advancedOptions.prompt, advancedOptions);
-```
-
 ## 📊 Performance Specifications
 
 ### Model Architecture
@@ -190,43 +136,6 @@ const image = await generator(advancedOptions.prompt, advancedOptions);
 
 *All browsers support WebAssembly fallback for universal compatibility*
 
-## ⚙️ Configuration Options
-
-### Generation Parameters
-
-```javascript
-const generationConfig = {
-  // Core settings
-  num_inference_steps: 20,      // 10-50 (quality vs speed trade-off)
-  guidance_scale: 7.5,          // 1.0-20.0 (prompt adherence)
-  height: 512,                  // Must be multiple of 64
-  width: 512,                   // Must be multiple of 64
-  
-  // Quality settings
-  negative_prompt: "blurry, low quality, distorted",
-  seed: undefined,              // Random seed, or integer for reproducibility
-  
-  // Performance optimizations
-  enable_attention_slicing: true,    // Reduces VRAM usage
-  enable_sequential_cpu_offload: false,  // CPU fallback for components
-  use_fp16: true                     // Half precision for speed/memory
-};
-```
-
-### Memory Optimization
-
-For devices with limited VRAM or older hardware:
-
-```javascript
-const memoryOptimizedConfig = {
-  num_inference_steps: 15,           // Fewer steps = less memory
-  guidance_scale: 7.0,               // Slightly lower guidance
-  enable_attention_slicing: true,     // Essential for <6GB VRAM
-  enable_sequential_cpu_offload: true,    // Move components to CPU when needed
-  use_safety_checker: false          // Disable to save ~600MB
-};
-```
-
 ## 📝 Model Details
 
 ### Training Information