Update README.md

README.md

@@ -60,8 +60,40 @@ pip install -r requirements.txt
 pip install -e .
 ```
 
+### 🚀 Easy Usage
+
+PosterCraft is designed as a unified and flexible framework. This makes it easy to use PosterCraft within your own custom workflows or other compatible frameworks.
+
+Loading the model is straightforward:
+
+```python
+import torch
+from diffusers import FluxPipeline, FluxTransformer2DModel
+
+# 1. Define model IDs and settings
+pipeline_id = "black-forest-labs/FLUX.1-dev"
+postercraft_transformer_id = "PosterCraft/PosterCraft-v1_RL" 
+device = "cuda"
+dtype = torch.bfloat16
+
+# 2. Load the base pipeline
+pipe = FluxPipeline.from_pretrained(pipeline_id, torch_dtype=dtype)
+
+# 3. The key step: simply replace the original transformer with our fine-tuned PosterCraft model
+pipe.transformer = FluxTransformer2DModel.from_pretrained(
+    postercraft_transformer_id, 
+    torch_dtype=dtype
+)
+pipe.to(device)
+
+# Now, `pipe` is a standard diffusers pipeline ready for inference with your own logic.
+
+```
+
 ### 🚀 Quick Generation
 
+For the best results and to leverage our intelligent prompt rewriting feature, we recommend using the provided `inference.py` script. This script automatically enhances your creative ideas for optimal results.
+
 Generate high-quality aesthetic posters from your prompt with `BF16` precision, please refer to our [GitHub repository](https://github.com/Ephemeral182/PosterCraft) :
 
 ```bash
@@ -76,9 +108,11 @@ python inference.py \
   --qwen_model_path "Qwen/Qwen3-8B"
 ```
 
+
+
 ### 💻 Gradio Web UI
 
-We provide a Gradio web UI for PosterCraft. 
+We provide a Gradio web UI for PosterCraft, please refer to our [GitHub repository](https://github.com/Ephemeral182/PosterCraft). 
 
 ```bash
 python -m gradio poster_craft_web_ui.py