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

[Frontend] Rewrite video API for async job lifecycle (#1665)

Browse Source 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
Co-authored-by: Gao Han <gaohan19@huawei.com>
This commit is contained in:
Ian EavesSamitGao Han
 authored and GitHub committed 2026-03-13 17:11:06 +08:00
1 parent e0b71056ba
commit 92f771d455
22 files changed
+2001 -372
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/examples/online_serving/image_to_video.md
+116 -2
View File
@@ -29,6 +29,35 @@ The script allows overriding:
- `CACHE_BACKEND` (default: `none`)
- `ENABLE_CACHE_DIT_SUMMARY` (default: `0`)
## Async Job Behavior
`POST /v1/videos` is asynchronous. It creates a video job and immediately
returns metadata like the job ID and initial `queued` status. To get the final
artifact, poll the job status and then download the completed file from the
content endpoint.
The main endpoints are:
- `POST /v1/videos`: create a video generation job
- `GET /v1/videos/{video_id}`: retrieve the current job status and metadata
- `GET /v1/videos`: list stored video jobs
- `GET /v1/videos/{video_id}/content`: download the generated video file
- `DELETE /v1/videos/{video_id}`: delete the job and any stored output
## Storage
Generated video files are stored on local disk by the async video API.
Local file storage behavior can be controlled via the following environment variables:
- `VLLM_OMNI_STORAGE_PATH`: directory used for generated files (default: `/tmp/storage`)
- `VLLM_OMNI_STORAGE_MAX_CONCURRENCY`: max concurrent save/delete operations (default: `4`)
Example:
```bash
export VLLM_OMNI_STORAGE_PATH=/var/tmp/vllm-omni-videos
export VLLM_OMNI_STORAGE_MAX_CONCURRENCY=8
```
## API Calls
### Method 1: Using curl
@@ -38,7 +67,7 @@ The script allows overriding:
bash run_curl_image_to_video.sh
# Or execute directly (OpenAI-style multipart)
curl -X POST http://localhost:8091/v1/videos \
create_response=$(curl -s http://localhost:8091/v1/videos \
-H "Accept: application/json" \
-F "prompt=A bear playing with yarn, smooth motion" \
-F "negative_prompt=low quality, blurry, static" \
@@ -52,7 +81,23 @@ curl -X POST http://localhost:8091/v1/videos \
-F "guidance_scale_2=1.0" \
-F "boundary_ratio=0.875" \
-F "flow_shift=12.0" \
-F "seed=42" | jq -r '.data[0].b64_json' | base64 -d > wan22_i2v_output.mp4
-F "seed=42")
video_id=$(echo "$create_response" | jq -r '.id')
while true; do
status=$(curl -s "http://localhost:8091/v1/videos/${video_id}" | jq -r '.status')
if [ "$status" = "completed" ]; then
break
fi
if [ "$status" = "failed" ]; then
echo "Video generation failed"
exit 1
fi
sleep 2
done
curl -s "http://localhost:8091/v1/videos/${video_id}" | jq .
curl -L "http://localhost:8091/v1/videos/${video_id}/content" -o wan22_i2v_output.mp4
```
## Request Format
@@ -66,6 +111,18 @@ curl -X POST http://localhost:8091/v1/videos \
-F "input_reference=@/path/to/qwen-bear.png"
```
### Alternative JSON-Safe Reference Input
Use `image_reference` when you want to pass a URL or JSON-safe image reference
instead of uploading a file. Do not send `input_reference` and
`image_reference` together.
```bash
curl -X POST http://localhost:8091/v1/videos \
-F "prompt=A bear playing with yarn, smooth motion" \
-F 'image_reference={"image_url":"https://example.com/qwen-bear.png"}'
```
### Generation with Parameters
```bash
@@ -85,6 +142,63 @@ curl -X POST http://localhost:8091/v1/videos \
-F "seed=42"
```
## Create Response Format
`POST /v1/videos` returns a job record.
```json
{
"id": "video_gen_123",
"object": "video",
"status": "queued",
"model": "Wan-AI/Wan2.2-I2V-A14B-Diffusers",
"prompt": "A bear playing with yarn, smooth motion",
"created_at": 1234567890
}
```
## Retrieve, List, Download, and Delete
### Retrieve a job
```bash
curl -s http://localhost:8091/v1/videos/${video_id} | jq .
```
### List jobs
```bash
curl -s http://localhost:8091/v1/videos | jq .
```
### Download the completed video
```bash
curl -L http://localhost:8091/v1/videos/${video_id}/content -o wan22_i2v_output.mp4
```
### Delete a job and its stored file
```bash
curl -X DELETE http://localhost:8091/v1/videos/${video_id} | jq .
```
## Poll Until Complete
```bash
while true; do
status=$(curl -s http://localhost:8091/v1/videos/${video_id} | jq -r '.status')
if [ "$status" = "completed" ]; then
break
fi
if [ "$status" = "failed" ]; then
echo "Video generation failed"
exit 1
fi
sleep 2
done
```
## Example materials
??? abstract "run_curl_image_to_video.sh"
docs/user_guide/examples/online_serving/text_to_video.md
+96 -12
View File
@@ -29,6 +29,34 @@ The script allows overriding:
- `CACHE_BACKEND` (default: `none`)
- `ENABLE_CACHE_DIT_SUMMARY` (default: `0`)
## Async Job Behavior
`POST /v1/videos` is asynchronous. It creates a video job and immediately
returns metadata like the job ID and initial `queued` status. To get the final
artifact, poll the job status and then download the completed file from the
content endpoint.
The main endpoints are:
- `POST /v1/videos`: create a video generation job
- `GET /v1/videos/{video_id}`: retrieve the current job status and metadata
- `GET /v1/videos`: list stored video jobs
- `GET /v1/videos/{video_id}/content`: download the generated video file
- `DELETE /v1/videos/{video_id}`: delete the job and any stored output
## Storage
Generated video files are stored on local disk by the async video API.
- `VLLM_OMNI_STORAGE_PATH`: directory used for generated files (default: `/tmp/storage`)
- `VLLM_OMNI_STORAGE_MAX_CONCURRENCY`: max concurrent save/delete operations (default: `4`)
Example:
```bash
export VLLM_OMNI_STORAGE_PATH=/var/tmp/vllm-omni-videos
export VLLM_OMNI_STORAGE_MAX_CONCURRENCY=8
```
## API Calls
### Method 1: Using curl
@@ -38,7 +66,7 @@ The script allows overriding:
bash run_curl_text_to_video.sh
# Or execute directly (OpenAI-style multipart)
curl -s http://localhost:8091/v1/videos \
create_response=$(curl -s http://localhost:8091/v1/videos \
-H "Accept: application/json" \
-F "prompt=Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage." \
-F "width=832" \
@@ -50,7 +78,24 @@ curl -s http://localhost:8091/v1/videos \
-F "guidance_scale=4.0" \
-F "guidance_scale_2=4.0" \
-F "boundary_ratio=0.875" \
-F "seed=42" | jq -r '.data[0].b64_json' | base64 -d > wan22_output.mp4
-F "flow_shift=5.0" \
-F "seed=42")
video_id=$(echo "$create_response" | jq -r '.id')
while true; do
status=$(curl -s "http://localhost:8091/v1/videos/${video_id}" | jq -r '.status')
if [ "$status" = "completed" ]; then
break
fi
if [ "$status" = "failed" ]; then
echo "Video generation failed"
exit 1
fi
sleep 2
done
curl -s "http://localhost:8091/v1/videos/${video_id}" | jq .
curl -L "http://localhost:8091/v1/videos/${video_id}/content" -o wan22_output.mp4
```
## Request Format
@@ -85,8 +130,9 @@ curl -X POST http://localhost:8091/v1/videos \
| Parameter | Type | Default | Description |
| --------------------- | ------ | ------- | ------------------------------------------------ |
| `prompt` | str | - | Text description of the desired video |
| `seconds` | str | None | Clip duration in seconds |
| `size` | str | None | Output size in `WIDTHxHEIGHT` format |
| `negative_prompt` | str | None | Negative prompt |
| `n` | int | 1 | Number of videos to generate |
| `width` | int | None | Video width in pixels |
| `height` | int | None | Video height in pixels |
| `num_frames` | int | None | Number of frames to generate |
@@ -98,24 +144,62 @@ curl -X POST http://localhost:8091/v1/videos \
| `flow_shift` | float | None | Scheduler flow shift (Wan2.2) |
| `seed` | int | None | Random seed (reproducible) |
| `lora` | object | None | LoRA configuration |
| `extra_body` | object | None | Model-specific extra parameters |
## Response Format
## Create Response Format
`POST /v1/videos` returns a job record.
```json
{
"created": 1234567890,
"data": [
{ "b64_json": "<base64-mp4>" }
]
"id": "video_gen_123",
"object": "video",
"status": "queued",
"model": "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
"prompt": "A cinematic view of a futuristic city at sunset",
"created_at": 1234567890
}
```
## Extract Video
## Retrieve, List, Download, and Delete
### Retrieve a job
```bash
# Extract base64 from response and decode to video
cat response.json | jq -r '.data[0].b64_json' | base64 -d > wan22_output.mp4
curl -s http://localhost:8091/v1/videos/${video_id} | jq .
```
### List jobs
```bash
curl -s http://localhost:8091/v1/videos | jq .
```
### Download the completed video
```bash
curl -L http://localhost:8091/v1/videos/${video_id}/content -o wan22_output.mp4
```
### Delete a job and its stored file
```bash
curl -X DELETE http://localhost:8091/v1/videos/${video_id} | jq .
```
## Poll Until Complete
```bash
while true; do
status=$(curl -s http://localhost:8091/v1/videos/${video_id} | jq -r '.status')
if [ "$status" = "completed" ]; then
break
fi
if [ "$status" = "failed" ]; then
echo "Video generation failed"
exit 1
fi
sleep 2
done
```
## Example materials