anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Unifying CLI Argument Naming Style (#1309)

Browse Source 
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
This commit is contained in:
Didan Deng authored and GitHub committed 2026-02-11 17:17:48 +08:00
1 parent dd302b63c4
commit 8e3dce781e
32 files changed
+275 -275
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/examples/offline_inference/image_to_image.md
+13 -13
View File
@@ -22,8 +22,8 @@ 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
--num-inference-steps 50 \
--cfg-scale 4.0
```
### Multiple Image Editing (Qwen-Image-Edit-2509)
@@ -36,26 +36,26 @@ python image_edit.py \
--image img1.png img2.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
--num-inference-steps 50 \
--cfg-scale 4.0 \
--guidance-scale 1.0
```
Key arguments:
- `--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 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).
- `--prompt` / `--negative-prompt`: text description (string).
- `--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.
- `--vae_use_slicing`: enable VAE slicing for memory optimization.
- `--vae_use_tiling`: enable VAE tiling for memory optimization.
- `--cfg_parallel_size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](https://github.com/vllm-project/vllm-omni/tree/main/docs/user_guide/diffusion/parallelism_acceleration.md#cfg-parallel).
- `--vae-use-slicing`: enable VAE slicing for memory optimization.
- `--vae-use-tiling`: enable VAE tiling for memory optimization.
- `--cfg-parallel-size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](https://github.com/vllm-project/vllm-omni/tree/main/docs/user_guide/diffusion/parallelism_acceleration.md#cfg-parallel).
- `--enable-cpu-offload`: enable CPU offloading for diffusion models.
> ℹ️ If you encounter OOM errors, try using `--vae_use_slicing` and `--vae_use_tiling` to reduce memory usage.
> ℹ️ If you encounter OOM errors, try using `--vae-use-slicing` and `--vae-use-tiling` to reduce memory usage.
## Example materials
docs/user_guide/examples/offline_inference/image_to_video.md
+22 -22
View File
@@ -20,15 +20,15 @@ python image_to_video.py \
--model Wan-AI/Wan2.2-I2V-A14B-Diffusers \
--image cherry_blossom.jpg \
--prompt "Cherry blossoms swaying gently in the breeze, petals falling, smooth motion" \
--negative_prompt "<optional quality filter>" \
--negative-prompt "<optional quality filter>" \
--height 480 \
--width 832 \
--num_frames 48 \
--guidance_scale 5.0 \
--guidance_scale_high 6.0 \
--num_inference_steps 40 \
--boundary_ratio 0.875 \
--flow_shift 12.0 \
--num-frames 48 \
--guidance-scale 5.0 \
--guidance-scale-high 6.0 \
--num-inference-steps 40 \
--boundary-ratio 0.875 \
--flow-shift 12.0 \
--fps 16 \
--output i2v_output.mp4
```
@@ -40,13 +40,13 @@ python image_to_video.py \
--model Wan-AI/Wan2.2-TI2V-5B-Diffusers \
--image cherry_blossom.jpg \
--prompt "Cherry blossoms swaying gently in the breeze, petals falling, smooth motion" \
--negative_prompt "<optional quality filter>" \
--negative-prompt "<optional quality filter>" \
--height 480 \
--width 832 \
--num_frames 48 \
--guidance_scale 4.0 \
--num_inference_steps 40 \
--flow_shift 12.0 \
--num-frames 48 \
--guidance-scale 4.0 \
--num-inference-steps 40 \
--flow-shift 12.0 \
--fps 16 \
--output i2v_output.mp4
```
@@ -57,20 +57,20 @@ Key arguments:
- `--image`: Path to input image (required).
- `--prompt`: Text description of desired motion/animation.
- `--height/--width`: Output resolution (auto-calculated from image if not set). Dimensions should be multiples of 16.
- `--num_frames`: Number of frames (default 81).
- `--guidance_scale` and `--guidance_scale_high`: CFG scale (applied to low/high-noise stages for MoE).
- `--negative_prompt`: Optional list of artifacts to suppress.
- `--boundary_ratio`: Boundary split ratio for two-stage MoE models.
- `--flow_shift`: Scheduler flow shift (5.0 for 720p, 12.0 for 480p).
- `--num_inference_steps`: Number of denoising steps (default 50).
- `--num-frames`: Number of frames (default 81).
- `--guidance-scale` and `--guidance-scale-high`: CFG scale (applied to low/high-noise stages for MoE).
- `--negative-prompt`: Optional list of artifacts to suppress.
- `--boundary-ratio`: Boundary split ratio for two-stage MoE models.
- `--flow-shift`: Scheduler flow shift (5.0 for 720p, 12.0 for 480p).
- `--num-inference-steps`: Number of denoising steps (default 50).
- `--fps`: Frames per second for the saved MP4 (requires `diffusers` export_to_video).
- `--output`: Path to save the generated video.
- `--vae_use_slicing`: Enable VAE slicing for memory optimization.
- `--vae_use_tiling`: Enable VAE tiling for memory optimization.
- `--cfg_parallel_size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](https://github.com/vllm-project/vllm-omni/tree/main/docs/user_guide/diffusion/parallelism_acceleration.md#cfg-parallel).
- `--vae-use-slicing`: Enable VAE slicing for memory optimization.
- `--vae-use-tiling`: Enable VAE tiling for memory optimization.
- `--cfg-parallel-size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](https://github.com/vllm-project/vllm-omni/tree/main/docs/user_guide/diffusion/parallelism_acceleration.md#cfg-parallel).
- `--enable-cpu-offload`: enable CPU offloading for diffusion models.
> ℹ️ If you encounter OOM errors, try using `--vae_use_slicing` and `--vae_use_tiling` to reduce memory usage.
> ℹ️ If you encounter OOM errors, try using `--vae-use-slicing` and `--vae-use-tiling` to reduce memory usage.
## Example materials
docs/user_guide/examples/offline_inference/lora_inference.md
+4 -4
View File
@@ -26,7 +26,7 @@ python -m examples.offline_inference.lora_inference.lora_inference \
--prompt "A piece of cheesecake" \
--lora-path /path/to/lora/ \
--lora-scale 1.0 \
--num_inference_steps 50 \
--num-inference-steps 50 \
--height 1024 \
--width 1024 \
--output output_preloaded.png
@@ -43,7 +43,7 @@ python -m examples.offline_inference.lora_inference.lora_inference \
--prompt "A piece of cheesecake" \
--lora-request-path /path/to/lora/ \
--lora-scale 1.0 \
--num_inference_steps 50 \
--num-inference-steps 50 \
--height 1024 \
--width 1024 \
--output output_per_request.png
@@ -56,7 +56,7 @@ If no LoRA request is provided, we will use the base model without any LoRA adap
```bash
python -m examples.offline_inference.lora_inference.lora_inference \
--prompt "A piece of cheesecake" \
--num_inference_steps 50 \
--num-inference-steps 50 \
--height 1024 \
--width 1024 \
--output output_no_lora.png
@@ -77,7 +77,7 @@ python -m examples.offline_inference.lora_inference.lora_inference \
- `--seed`: Random seed for reproducibility (default: 42)
- `--height`: Image height in pixels (default: 1024)
- `--width`: Image width in pixels (default: 1024)
- `--num_inference_steps`: Number of denoising steps (default: 50)
- `--num-inference-steps`: Number of denoising steps (default: 50)
- `--output`: Output file path (default: `lora_output.png`)
## How LoRA Works
docs/user_guide/examples/offline_inference/text_to_audio.md
+8 -8
View File
@@ -21,22 +21,22 @@ If you use a gated model (e.g., `stabilityai/stable-audio-open-1.0`), ensure you
python text_to_audio.py \
--model stabilityai/stable-audio-open-1.0 \
--prompt "The sound of a hammer hitting a wooden surface" \
--negative_prompt "Low quality" \
--negative-prompt "Low quality" \
--seed 42 \
--guidance_scale 7.0 \
--audio_length 10.0 \
--num_inference_steps 100 \
--guidance-scale 7.0 \
--audio-length 10.0 \
--num-inference-steps 100 \
--output stable_audio_output.wav
```
Key arguments:
- `--prompt`: text description (string).
- `--negative_prompt`: negative prompt for classifier-free guidance.
- `--negative-prompt`: negative prompt for classifier-free guidance.
- `--seed`: integer seed for deterministic generation.
- `--guidance_scale`: classifier-free guidance scale.
- `--audio_length`: audio duration in seconds.
- `--num_inference_steps`: diffusion sampling steps.(more steps = higher quality, slower).
- `--guidance-scale`: classifier-free guidance scale.
- `--audio-length`: audio duration in seconds.
- `--num-inference-steps`: diffusion sampling steps.(more steps = higher quality, slower).
- `--output`: path to save the generated WAV file.
## Example materials
docs/user_guide/examples/offline_inference/text_to_image.md
+10 -10
View File
@@ -82,9 +82,9 @@ 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 \
--num_images_per_prompt 1 \
--num_inference_steps 50 \
--cfg-scale 4.0 \
--num-images-per-prompt 1 \
--num-inference-steps 50 \
--height 1024 \
--width 1024 \
--output outputs/coffee.png
@@ -94,17 +94,17 @@ Key arguments:
- `--prompt`: text description (string).
- `--seed`: integer seed for deterministic sampling.
- `--cfg_scale`: true CFG scale (model-specific guidance strength).
- `--num_images_per_prompt`: number of images to generate per prompt (saves as `output`, `output_1`, ...).
- `--num_inference_steps`: diffusion sampling steps (more steps = higher quality, slower).
- `--cfg-scale`: true CFG scale (model-specific guidance strength).
- `--num-images-per-prompt`: number of images to generate per prompt (saves as `output`, `output_1`, ...).
- `--num-inference-steps`: diffusion sampling steps (more steps = higher quality, slower).
- `--height/--width`: output resolution (defaults 1024x1024).
- `--output`: path to save the generated PNG.
- `--vae_use_slicing`: enable VAE slicing for memory optimization.
- `--vae_use_tiling`: enable VAE tiling for memory optimization.
- `--cfg_parallel_size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](https://github.com/vllm-project/vllm-omni/tree/main/docs/user_guide/diffusion/parallelism_acceleration.md#cfg-parallel).
- `--vae-use-slicing`: enable VAE slicing for memory optimization.
- `--vae-use-tiling`: enable VAE tiling for memory optimization.
- `--cfg-parallel-size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](https://github.com/vllm-project/vllm-omni/tree/main/docs/user_guide/diffusion/parallelism_acceleration.md#cfg-parallel).
- `--enable-cpu-offload`: enable CPU offloading for diffusion models.
> ℹ️ If you encounter OOM errors, try using `--vae_use_slicing` and `--vae_use_tiling` to reduce memory usage.
> ℹ️ If you encounter OOM errors, try using `--vae-use-slicing` and `--vae-use-tiling` to reduce memory usage.
> 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.
docs/user_guide/examples/offline_inference/text_to_video.md
+14 -14
View File
@@ -10,14 +10,14 @@ The `Wan-AI/Wan2.2-T2V-A14B-Diffusers` pipeline generates short videos from text
```bash
python text_to_video.py \
--prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage." \
--negative_prompt "<optional quality filter>" \
--negative-prompt "<optional quality filter>" \
--height 480 \
--width 832 \
--num_frames 33 \
--guidance_scale 4.0 \
--guidance_scale_high 3.0 \
--flow_shift 12.0 \
--num_inference_steps 40 \
--num-frames 33 \
--guidance-scale 4.0 \
--guidance-scale-high 3.0 \
--flow-shift 12.0 \
--num-inference-steps 40 \
--fps 16 \
--output t2v_out.mp4
```
@@ -26,18 +26,18 @@ Key arguments:
- `--prompt`: text description (string).
- `--height/--width`: output resolution (defaults 480x832, i.e. 480P). Dimensions should align with Wan VAE downsampling (multiples of 8).
- `--num_frames`: Number of frames (Wan default is 81).
- `--guidance_scale` and `--guidance_scale_high`: CFG scale (applied to low/high).
- `--negative_prompt`: optional list of artifacts to suppress (the PR demo used a long Chinese string).
- `--boundary_ratio`: Boundary split ratio for low/high DiT. Default `0.875` uses both transformers for best quality. Set to `1.0` to load only the low-noise transformer (saves noticeable memory with good quality, recommended if memory is limited). Set to `0.0` loads only the high-noise transformer (not recommended, lower quality).
- `--num-frames`: Number of frames (Wan default is 81).
- `--guidance-scale` and `--guidance-scale-high`: CFG scale (applied to low/high).
- `--negative-prompt`: optional list of artifacts to suppress (the PR demo used a long Chinese string).
- `--boundary-ratio`: Boundary split ratio for low/high DiT. Default `0.875` uses both transformers for best quality. Set to `1.0` to load only the low-noise transformer (saves noticeable memory with good quality, recommended if memory is limited). Set to `0.0` loads only the high-noise transformer (not recommended, lower quality).
- `--fps`: frames per second for the saved MP4 (requires `diffusers` export_to_video).
- `--output`: path to save the generated video.
- `--vae_use_slicing`: enable VAE slicing for memory optimization.
- `--vae_use_tiling`: enable VAE tiling for memory optimization.
- `--cfg_parallel_size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](https://github.com/vllm-project/vllm-omni/tree/main/docs/user_guide/diffusion/parallelism_acceleration.md#cfg-parallel).
- `--vae-use-slicing`: enable VAE slicing for memory optimization.
- `--vae-use-tiling`: enable VAE tiling for memory optimization.
- `--cfg-parallel-size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](https://github.com/vllm-project/vllm-omni/tree/main/docs/user_guide/diffusion/parallelism_acceleration.md#cfg-parallel).
- `--enable-cpu-offload`: enable CPU offloading for diffusion models.
> ℹ️ If you encounter OOM errors, try using `--vae_use_slicing` and `--vae_use_tiling` to reduce memory usage.
> ℹ️ If you encounter OOM errors, try using `--vae-use-slicing` and `--vae-use-tiling` to reduce memory usage.
## Example materials