[Model] Support Qwen-Image-Edit 2509 ( multi-image input edit) (#330)

Signed-off-by: samithuang <285365963@qq.com>

docs/user_guide/examples/offline_inference/image_to_image.md

@@ -7,20 +7,40 @@ This example edits an input image with `Qwen/Qwen-Image-Edit` using the `image_e
 
 ## Local CLI Usage
 
+### Single Image Editing
+
 ```bash
 python image_edit.py \
   --image qwen_bear.png \
   --prompt "Let this mascot dance under the moon, surrounded by floating stars and poetic bubbles such as 'Be Kind'" \
   --output output_image_edit.png \
   --num_inference_steps 50 \
-  --cfg_scale 4.0
+  --cfg_scale 4.0 \
+  --guidance_scale 1.0
+```
+
+### Multiple Image Editing (Qwen-Image-Edit-2509+)
+
+For multiple image inputs, use `Qwen/Qwen-Image-Edit-2509` or later version:
+
+```bash
+python image_edit.py \
+  --model Qwen/Qwen-Image-Edit-2509 \
+  --image img1.png img2.png img3.png \
+  --prompt "Combine these images into a single scene" \
+  --output output_image_edit.png \
+  --num_inference_steps 50 \
+  --cfg_scale 4.0 \
+  --guidance_scale 1.0
 ```
 
 Key arguments:
 
-- `--image`: path to the source image (PNG/JPG, converted to RGB).
+- `--model`: model name or path. Use `Qwen/Qwen-Image-Edit-2509` or later for multiple image support.
+- `--image`: path(s) to the source image(s) (PNG/JPG, converted to RGB). Can specify multiple images.
 - `--prompt` / `--negative_prompt`: text description (string).
-- `--cfg_scale`: true CFG scale for Qwen-Image-Edit (quality vs. fidelity).
+- `--cfg_scale`: true classifier-free guidance scale (default: 4.0). Classifier-free guidance is enabled by setting cfg_scale > 1 and providing a negative_prompt. Higher guidance scale encourages images closely linked to the text prompt, usually at the expense of lower image quality.
+- `--guidance_scale`: guidance scale for guidance-distilled models (default: 1.0, disabled). Unlike classifier-free guidance (--cfg_scale), guidance-distilled models take the guidance scale directly as an input parameter. Enabled when guidance_scale > 1. Ignored when not using guidance-distilled models.
 - `--num_inference_steps`: diffusion sampling steps (more steps = higher quality, slower).
 - `--output`: path to save the generated PNG.