[Docs] Add basic usage examples for diffusion (#222)

Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

docs/getting_started/quickstart.md

@@ -16,7 +16,19 @@ Please refer to [installation](installation/README.md)
 
 ## Offline Inference
 
-Please refer to [offline inference](../user_guide/examples/offline_inference/qwen2_5_omni.md)
+Text-to-image generation quickstart with vLLM-Omni:
+
+```python
+from vllm_omni.entrypoints.omni import Omni
+
+if __name__ == "__main__":
+    omni = Omni(model="Tongyi-MAI/Z-Image-Turbo")
+    prompt = "a cup of coffee on the table"
+    images = omni.generate(prompt)
+    images[0].save("coffee.png")
+```
+
+For more usages, please refer to [offline inference](../user_guide/examples/offline_inference/qwen2_5_omni.md)
 
 ## Online Serving with OpenAI-Completions API
 

examples/offline_inference/qwen_image/README.md

@@ -1,10 +1,21 @@
 # Qwen-Image Offline Inference
 
-This folder provides two simple entrypoints for experimenting with `Qwen/Qwen-Image` using vLLM-Omni:
+This folder provides several entrypoints for experimenting with `Qwen/Qwen-Image` using vLLM-Omni:
 
-- `text_to_image.py`: command-line script for single image generation.
+- `text_to_image.py`: command-line script for single image generation with advanced options.
 - `web_demo.py`: lightweight Gradio UI for interactive prompt/seed/CFG exploration.
 
+## Basic Usage
+
+```python
+from vllm_omni.entrypoints.omni import Omni
+
+if __name__ == "__main__":
+    omni = Omni(model="Qwen/Qwen-Image")
+    prompt = "a cup of coffee on the table"
+    images = omni.generate(prompt)
+    images[0].save("coffee.png")
+```
 
 ## Local CLI Usage
 

examples/offline_inference/qwen_image/gradio_demo.py

@@ -105,7 +105,6 @@ def build_demo(args: argparse.Namespace) -> gr.Blocks:
             generator=generator,
             true_cfg_scale=float(cfg_scale_value),
             num_inference_steps=num_steps,
-            num_images_per_prompt=num_images,
             num_outputs_per_prompt=num_images,
         )
         return [img for img in images[:num_images]]

examples/offline_inference/qwen_image/text_to_image.py

@@ -65,7 +65,6 @@ def main():
         generator=generator,
         true_cfg_scale=args.cfg_scale,
         num_inference_steps=args.num_inference_steps,
-        num_images_per_prompt=args.num_images_per_prompt,
         num_outputs_per_prompt=args.num_images_per_prompt,
     )