[Doc] fix offline inference and online serving describe (#285)

Signed-off-by: David Chen <530634352@qq.com>

docs/user_guide/examples/offline_inference/image_to_image.md

@@ -1,7 +1,8 @@
-# Qwen-Image-Edit Offline Inference
+# Image-To-Image
 
 Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/image_to_image>. Added in PR [#196](https://github.com/vllm-project/vllm-omni/pull/196).
 
+
 This example edits an input image with `Qwen/Qwen-Image-Edit` using the `image_edit.py` CLI.
 
 ## Local CLI Usage
@@ -16,6 +17,7 @@ python image_edit.py \
 ```
 
 Key arguments:
+
 - `--image`: path to the source image (PNG/JPG, converted to RGB).
 - `--prompt` / `--negative_prompt`: text description (string).
 - `--cfg_scale`: true CFG scale for Qwen-Image-Edit (quality vs. fidelity).

docs/user_guide/examples/offline_inference/qwen2_5_omni.md

@@ -1,4 +1,4 @@
-# Offline Example of vLLM-Omni for Qwen2.5-Omni
+# Qwen2.5-Omni
 
 Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/qwen2_5_omni>.
 

docs/user_guide/examples/offline_inference/qwen3_omni.md

@@ -1,4 +1,4 @@
-# Offline Example of vLLM-Omni for Qwen3-Omni
+# Qwen3-Omni
 
 Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/qwen3_omni>.
 

docs/user_guide/examples/offline_inference/text_to_image.md

@@ -1,4 +1,4 @@
-# Qwen-Image Offline Inference
+# Text-To-Image
 
 Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/text_to_image>.
 
@@ -34,6 +34,8 @@ Key arguments:
 - `--height/--width`: output resolution (defaults 1024x1024).
 - `--output`: path to save the generated PNG.
 
+> ℹ️ Qwen-Image currently publishes best-effort presets at `1328x1328`, `1664x928`, `928x1664`, `1472x1140`, `1140x1472`, `1584x1056`, and `1056x1584`. Adjust `--height/--width` accordingly for the most reliable outcomes.
+
 ## Web UI Demo
 
 Launch the gradio demo:

docs/user_guide/examples/offline_inference/text_to_video.md

@@ -1,7 +1,8 @@
-# Wan2.2 Text-to-Video Offline Inference
+# Text-To-Video
 
 Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/text_to_video>. Added in PR [#202](https://github.com/vllm-project/vllm-omni/pull/202).
 
+
 The `Wan-AI/Wan2.2-T2V-A14B-Diffusers` pipeline generates short videos from text prompts.
 
 ## Local CLI Usage
@@ -21,6 +22,7 @@ python text_to_video.py \
 ```
 
 Key arguments:
+
 - `--prompt`: text description (string).
 - `--height/--width`: output resolution (defaults 720x1280). Dimensions should align with Wan VAE downsampling (multiples of 8).
 - `--num_frames`: Number of frames (Wan default is 81).

docs/user_guide/examples/online_serving/qwen2_5_omni.md

@@ -1,4 +1,4 @@
-# Online serving Example of vLLM-Omni for Qwen2.5-Omni
+# Qwen2.5-Omni
 
 Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/online_serving/qwen2_5_omni>.
 

docs/user_guide/examples/online_serving/qwen3_omni.md

@@ -1,4 +1,4 @@
-# Online serving Example of vLLM-Omni for Qwen3-omni
+# Qwen3-Omni
 
 Source <https://github.com/vllm-project/vllm-omni/tree/main/examples/online_serving/qwen3_omni>.