Upload README.md with huggingface_hub

README.md

@@ -38,7 +38,7 @@ tags:
   - hindi
   - spanish
   - portuguese
-short_description: Image Gen & Edit with GLM-4.6V + DeepSeek-3.2
+short_description: Image Gen & Transform. Van Gogh and Picasso style included!
 ---
 
 # ⚡ Z-Image Generation & Transformation Demo
@@ -48,33 +48,37 @@ Generate stunning AI images and transform existing photos using **Alibaba's Z-Im
 ## ✨ Features
 
 🎨 **Text-to-Image Generation**
-- 10 style presets (Photorealistic, Cinematic, Anime, Digital Art, and more)
+- 12 style presets (Photorealistic, Cinematic, Anime, Van Gogh, Picasso, and more)
 - 18 aspect ratios from 1024px to 2048px
-- AI-powered prompt polishing with Qwen2.5-72B
+- AI-powered prompt polishing with DeepSeek Reasoner
 
 🖼️ **Image-to-Image Transformation**
 - Transform photos into different art styles
+- **Van Gogh style**: Post-impressionist swirling brushstrokes, thick impasto, vibrant colors
+- **Picasso style**: Cubist geometric fragmentation, multiple perspectives, bold outlines
+- Style-only transformation: just select a style, no prompt needed!
 - Adjustable strength control (subtle to complete change)
-- Style-focused AI prompt enhancement
 
 ⚡ **Optimized Performance**
 - Runs on ZeroGPU (NVIDIA H200)
-- FlashAttention-2 via SDPA
+- FlashAttention-3 via kernels library
+- TF32 + VAE torch.compile optimization
 - ~20-25 seconds per generation
 
 ## 🚀 How to Use
 
 ### Generate Tab
 1. Enter a description of your image
-2. (Optional) Enable "Polish Prompt" for AI-enhanced prompts
+2. (Optional) Enable "Prompt+" for AI-enhanced prompts
 3. Select a style and aspect ratio
 4. Click "Generate"
 
 ### Transform Tab
 1. Upload an image
-2. Describe the transformation you want
-3. Adjust strength (lower = subtle, higher = dramatic)
-4. Click "Transform"
+2. Select a style (Van Gogh, Picasso, etc.) - **no prompt needed!**
+3. Or add a custom prompt for more control
+4. Adjust strength (lower = subtle, higher = dramatic)
+5. Click "Transform"
 
 ## 🎯 Example Prompts