Update README.md

README.md

@@ -15,15 +15,108 @@ base_model:
 
 ## ✨ Z-Image-Turbo FP32 / FP16 / BF16 EMA-ONLY & FULL
 
-Used script [merge-safetensors](https://github.com/dkotel/merge-safetensors) to merge transformer parts into one `*.safetensors` file(placed in `transformer` directory).
-Used script [PyTorch-Precision-Converter](https://github.com/angelolamonaca/PyTorch-Precision-Converter) to transform full fp32 model into fp32/fp16/bf16 - full/ema-only model versions.
+Multiple versions of Z-Image-Turbo model in various precisions and configurations, prepared directly from the original [Tongyi-MAI/Z-Image-Turbo](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo) repository.
 
+## 📦 Available Variants
 
+| Type | Precision | Size | Description |
+|------|-----------|------|-------------|
+| **Full** | FP32/FP16/BF16 | Largest | Complete model with training and EMA parameters |
+| **EMA-only** | FP32/FP16/BF16 | Smaller | Only EMA parameters - **recommended for inference** |
 
-### THIS IS NOT FOR COMFYUI BUT FOR DIFFUSERS LIBRARY
-#### YOU HAVE TO RENAME TEXT ENCODER MODEL TO `model.safetensors`, TRANSFORMER/VAE MODEL TO `diffusion_pytorch_model.safetensors` AND PUT THEM IN THEIR APPROPRIATE FOLDERS IF YOU WANT TO USE IT WITH `ZImagePipeline` WITHOUT SPECIFYING THE EXACT PATH TO THE MODEL FILE.
+### EMA vs Full - Which to Choose?
 
+- **EMA-only**: Contains only Exponential Moving Average parameters - averaged weights from training process. Provides more stable and better results during image generation, smaller file size. **Use this for inference.**
+  
+- **Full**: Contains all parameters (training + EMA). Only needed if you want to continue training the model.
 
+## 🔧 Preparation Process
+
+Models were processed using:
+
+1. **[merge-safetensors](https://github.com/dkotel/merge-safetensors)** - merging split transformer parts into single `*.safetensors` file (placed in `transformer` directory)
+
+2. **[PyTorch-Precision-Converter](https://github.com/angelolamonaca/PyTorch-Precision-Converter)** - converting precision from FP32 to FP16/BF16 and creating EMA-only variants
+
+## 💡 For Diffusers Users
+
+> ⚠️ **This is NOT compatible with ComfyUI** - models are prepared for `diffusers` library.
+
+### Required File Names
+
+To use with `ZImagePipeline` without specifying full paths:
+```
+text_encoder/
+  └── model.safetensors              # Text encoder
+
+transformer/
+  └── diffusion_pytorch_model.safetensors   # Transformer
+
+vae/
+  └── diffusion_pytorch_model.safetensors   # VAE
+```
+
+### Example Usage (based on one from original repo)
+
+`pip install git+https://github.com/huggingface/diffusers`
+
+
+```python
+import torch
+from diffusers import ZImagePipeline
+
+# 1. Load the pipeline
+# Use bfloat16 for optimal performance on supported GPUs
+pipe = ZImagePipeline.from_pretrained(
+    "path/to/model_files_main_dir",
+    torch_dtype=torch.float32, # or torch.bfloat16 / torch.float16
+    low_cpu_mem_usage=False,
+)
+pipe.to("cuda")
+
+# [Optional] Attention Backend
+# Diffusers uses SDPA by default. Switch to Flash Attention for better efficiency if supported:
+# pipe.transformer.set_attention_backend("flash")    # Enable Flash-Attention-2
+# pipe.transformer.set_attention_backend("_flash_3") # Enable Flash-Attention-3
+
+# [Optional] Model Compilation
+# Compiling the DiT model accelerates inference, but the first run will take longer to compile.
+# pipe.transformer.compile()
+
+# [Optional] CPU Offloading
+# Enable CPU offloading for memory-constrained devices.
+# pipe.enable_model_cpu_offload()
+
+prompt = "Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. Neon lightning-bolt lamp (⚡️), bright yellow glow, above extended left palm. Soft-lit outdoor night background, silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights."
+
+# 2. Generate Image
+image = pipe(
+    prompt=prompt,
+    height=1024,
+    width=1024,
+    num_inference_steps=9,  # This actually results in 8 DiT forwards
+    guidance_scale=0.0,     # Guidance should be 0 for the Turbo models
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+
+image.save("example.png")
+
+```
+
+## 🎯 Recommendations
+
+- **RTX 3060 and similar**: Use **BF16** or **FP16** for optimal performance
+- **Less than 12GB VRAM**: **FP16 EMA-only** 
+- **12GB+ VRAM**: **BF16 EMA-only** (better numerical stability)
+- **Training**: **FP32 Full**
+
+## 📝 License
+
+Same as original [Z-Image-Turbo](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo) model.
+
+
+
+README was generated with a help of AI
 
 
 ```bibtex