From 7c8e5be627ac01b66b37bd0aed727d7001f7e369 Mon Sep 17 00:00:00 2001 From: WeiQing Chen <40507679+david6666666@users.noreply.github.com> Date: Fri, 12 Dec 2025 15:14:52 +0800 Subject: [PATCH] [Doc] fix offline inference and online serving describe (#285) Signed-off-by: David Chen <530634352@qq.com> --- .../examples/offline_inference/image_to_image.md | 4 +++- .../examples/offline_inference/qwen2_5_omni.md | 2 +- .../examples/offline_inference/qwen3_omni.md | 2 +- .../examples/offline_inference/text_to_image.md | 4 +++- .../examples/offline_inference/text_to_video.md | 4 +++- .../examples/online_serving/qwen2_5_omni.md | 2 +- .../user_guide/examples/online_serving/qwen3_omni.md | 2 +- .../image_to_image/image_to_image.md | 12 ++---------- examples/offline_inference/qwen2_5_omni/README.md | 2 +- examples/offline_inference/qwen3_omni/README.md | 2 +- examples/offline_inference/text_to_image/README.md | 5 +++-- .../offline_inference/text_to_video/text_to_video.md | 12 ++---------- examples/online_serving/qwen2_5_omni/README.md | 2 +- examples/online_serving/qwen3_omni/README.md | 2 +- 14 files changed, 24 insertions(+), 33 deletions(-) diff --git a/docs/user_guide/examples/offline_inference/image_to_image.md b/docs/user_guide/examples/offline_inference/image_to_image.md index 5bdb8ecd9..d0b321b8d 100644 --- a/docs/user_guide/examples/offline_inference/image_to_image.md +++ b/docs/user_guide/examples/offline_inference/image_to_image.md @@ -1,7 +1,8 @@ -# Qwen-Image-Edit Offline Inference +# Image-To-Image Source . 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). diff --git a/docs/user_guide/examples/offline_inference/qwen2_5_omni.md b/docs/user_guide/examples/offline_inference/qwen2_5_omni.md index 01d46e74c..301d6981d 100644 --- a/docs/user_guide/examples/offline_inference/qwen2_5_omni.md +++ b/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 . diff --git a/docs/user_guide/examples/offline_inference/qwen3_omni.md b/docs/user_guide/examples/offline_inference/qwen3_omni.md index 069929a02..e07db6f14 100644 --- a/docs/user_guide/examples/offline_inference/qwen3_omni.md +++ b/docs/user_guide/examples/offline_inference/qwen3_omni.md @@ -1,4 +1,4 @@ -# Offline Example of vLLM-Omni for Qwen3-Omni +# Qwen3-Omni Source . diff --git a/docs/user_guide/examples/offline_inference/text_to_image.md b/docs/user_guide/examples/offline_inference/text_to_image.md index 14e7a699d..c698b93c6 100644 --- a/docs/user_guide/examples/offline_inference/text_to_image.md +++ b/docs/user_guide/examples/offline_inference/text_to_image.md @@ -1,4 +1,4 @@ -# Qwen-Image Offline Inference +# Text-To-Image Source . @@ -34,6 +34,8 @@ Key arguments: - `--height/--width`: output resolution (defaults 1024x1024). - `--output`: path to save the generated PNG. +> ℹī¸ 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: diff --git a/docs/user_guide/examples/offline_inference/text_to_video.md b/docs/user_guide/examples/offline_inference/text_to_video.md index 2e9c833c2..4804599ad 100644 --- a/docs/user_guide/examples/offline_inference/text_to_video.md +++ b/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 . 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). diff --git a/docs/user_guide/examples/online_serving/qwen2_5_omni.md b/docs/user_guide/examples/online_serving/qwen2_5_omni.md index b9d9a2f19..af1b16e39 100644 --- a/docs/user_guide/examples/online_serving/qwen2_5_omni.md +++ b/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 . diff --git a/docs/user_guide/examples/online_serving/qwen3_omni.md b/docs/user_guide/examples/online_serving/qwen3_omni.md index 2a14e9929..a47185457 100644 --- a/docs/user_guide/examples/online_serving/qwen3_omni.md +++ b/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 . diff --git a/examples/offline_inference/image_to_image/image_to_image.md b/examples/offline_inference/image_to_image/image_to_image.md index 5bdb8ecd9..2bd6d84e1 100644 --- a/examples/offline_inference/image_to_image/image_to_image.md +++ b/examples/offline_inference/image_to_image/image_to_image.md @@ -1,6 +1,4 @@ -# Qwen-Image-Edit Offline Inference - -Source . Added in PR [#196](https://github.com/vllm-project/vllm-omni/pull/196). +# Image-To-Image This example edits an input image with `Qwen/Qwen-Image-Edit` using the `image_edit.py` CLI. @@ -16,15 +14,9 @@ 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). - `--num_inference_steps`: diffusion sampling steps (more steps = higher quality, slower). - `--output`: path to save the generated PNG. - -## Example materials - -??? abstract "image_edit.py" - ``````py - --8<-- "examples/offline_inference/image_to_image/image_edit.py" - `````` diff --git a/examples/offline_inference/qwen2_5_omni/README.md b/examples/offline_inference/qwen2_5_omni/README.md index 4467af095..f71000b43 100644 --- a/examples/offline_inference/qwen2_5_omni/README.md +++ b/examples/offline_inference/qwen2_5_omni/README.md @@ -1,4 +1,4 @@ -# Offline Example of vLLM-Omni for Qwen2.5-Omni +# Qwen2.5-Omni ## 🛠ī¸ Installation diff --git a/examples/offline_inference/qwen3_omni/README.md b/examples/offline_inference/qwen3_omni/README.md index 3868c5d1e..1472a0a93 100644 --- a/examples/offline_inference/qwen3_omni/README.md +++ b/examples/offline_inference/qwen3_omni/README.md @@ -1,4 +1,4 @@ -# Offline Example of vLLM-Omni for Qwen3-Omni +# Qwen3-Omni ## 🛠ī¸ Installation diff --git a/examples/offline_inference/text_to_image/README.md b/examples/offline_inference/text_to_image/README.md index 078d9fda3..d6291076a 100644 --- a/examples/offline_inference/text_to_image/README.md +++ b/examples/offline_inference/text_to_image/README.md @@ -1,6 +1,6 @@ -# Qwen-Image Offline Inference +# Text-To-Image -This folder provides several entrypoints for experimenting with `Qwen/Qwen-Image` using vLLM-Omni: +This folder provides several entrypoints for experimenting with `Qwen/Qwen-Image` `Tongyi-MAI/Z-Image-Turbo` using vLLM-Omni: - `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. @@ -21,6 +21,7 @@ if __name__ == "__main__": ```bash python text_to_image.py \ + --model Tongyi-MAI/Z-Image-Turbo \ --prompt "a cup of coffee on the table" \ --seed 42 \ --cfg_scale 4.0 \ diff --git a/examples/offline_inference/text_to_video/text_to_video.md b/examples/offline_inference/text_to_video/text_to_video.md index 2e9c833c2..a14bf1070 100644 --- a/examples/offline_inference/text_to_video/text_to_video.md +++ b/examples/offline_inference/text_to_video/text_to_video.md @@ -1,6 +1,4 @@ -# Wan2.2 Text-to-Video Offline Inference - -Source . Added in PR [#202](https://github.com/vllm-project/vllm-omni/pull/202). +# Text-To-Video The `Wan-AI/Wan2.2-T2V-A14B-Diffusers` pipeline generates short videos from text prompts. @@ -21,6 +19,7 @@ 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). @@ -29,10 +28,3 @@ Key arguments: - `--boundary_ratio`: Boundary split ratio for low/high DiT. - `--fps`: frames per second for the saved MP4 (requires `diffusers` export_to_video). - `--output`: path to save the generated video. - -## Example materials - -??? abstract "text_to_video.py" - ``````py - --8<-- "examples/offline_inference/wan22/text_to_video.py" - `````` diff --git a/examples/online_serving/qwen2_5_omni/README.md b/examples/online_serving/qwen2_5_omni/README.md index 28f3e61af..a9cca1076 100644 --- a/examples/online_serving/qwen2_5_omni/README.md +++ b/examples/online_serving/qwen2_5_omni/README.md @@ -1,4 +1,4 @@ -# Online serving Example of vLLM-Omni for Qwen2.5-Omni +# Qwen2.5-Omni ## 🛠ī¸ Installation diff --git a/examples/online_serving/qwen3_omni/README.md b/examples/online_serving/qwen3_omni/README.md index f5d5beab0..ee393fb13 100644 --- a/examples/online_serving/qwen3_omni/README.md +++ b/examples/online_serving/qwen3_omni/README.md @@ -1,4 +1,4 @@ -# Online serving Example of vLLM-Omni for Qwen3-omni +# Qwen3-Omni ## 🛠ī¸ Installation