Added clients, updated READMEs
This commit is contained in:
Lucas Armand
@@ -0,0 +1,168 @@
|
||||
# ComfyUI ACE Step PyWorker
|
||||
|
||||
This is the PyWorker implementation for running **ACE Step v1 3.5B** text-to-music workflows in ComfyUI. It provides a unified interface for executing complete ComfyUI audio-generation workflows through a proxy-based architecture and returning generated audio assets.
|
||||
|
||||
Each request has a static cost of `100`. ComfyUI does not support concurrent workloads, and there is no provision to run multiple ComfyUI instances per worker node.
|
||||
|
||||
## Requirements
|
||||
|
||||
This worker requires the following components:
|
||||
|
||||
- ComfyUI (https://github.com/comfyanonymous/ComfyUI)
|
||||
- ComfyUI API Wrapper (https://github.com/ai-dock/comfyui-api-wrapper)
|
||||
- ACE Step v1 3.5B model and required custom nodes
|
||||
|
||||
A Docker image is provided with the ACE Step model pre-installed, but any image may be used if the above requirements are met.
|
||||
|
||||
## Endpoint
|
||||
|
||||
The worker exposes a single synchronous endpoint:
|
||||
|
||||
- `/generate/sync`: Processes a complete ComfyUI workflow JSON and generates audio output
|
||||
|
||||
## Request Format
|
||||
|
||||
The ACE Step worker **only supports custom workflow mode**. Modifier-based workflows are not supported.
|
||||
|
||||
```json
|
||||
{
|
||||
"input": {
|
||||
"request_id": "uuid-string",
|
||||
"workflow_json": {
|
||||
// Complete ComfyUI ACE Step workflow JSON
|
||||
},
|
||||
"s3": { },
|
||||
"webhook": { }
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Request Fields
|
||||
|
||||
### Required Fields
|
||||
|
||||
- `input`: Container for all request parameters
|
||||
- `input.workflow_json`: Complete ComfyUI workflow graph for ACE Step audio generation
|
||||
|
||||
### Optional Fields
|
||||
|
||||
- `input.request_id`: Client-defined request identifier
|
||||
- `input.s3`: S3-compatible storage configuration
|
||||
- `input.webhook`: Webhook configuration for completion notifications
|
||||
|
||||
The special string `"__RANDOM_INT__"` may be used in the workflow JSON and will be replaced with a random integer before submission to ComfyUI.
|
||||
|
||||
## S3 Configuration
|
||||
|
||||
Generated audio assets can be automatically uploaded to S3-compatible storage. Configuration can be supplied per request or via environment variables. Request-level values take precedence.
|
||||
|
||||
### Via Request JSON
|
||||
|
||||
```json
|
||||
"s3": {
|
||||
"access_key_id": "your-s3-access-key",
|
||||
"secret_access_key": "your-s3-secret-access-key",
|
||||
"endpoint_url": "https://s3.amazonaws.com",
|
||||
"bucket_name": "your-bucket",
|
||||
"region": "us-east-1"
|
||||
}
|
||||
```
|
||||
|
||||
### Via Environment Variables
|
||||
|
||||
```bash
|
||||
S3_ACCESS_KEY_ID=your-key
|
||||
S3_SECRET_ACCESS_KEY=your-secret
|
||||
S3_BUCKET_NAME=your-bucket
|
||||
S3_ENDPOINT_URL=https://s3.amazonaws.com
|
||||
S3_REGION=us-east-1
|
||||
```
|
||||
|
||||
## Webhook Configuration
|
||||
|
||||
Webhooks are triggered on request completion or failure.
|
||||
|
||||
### Via Request JSON
|
||||
|
||||
```json
|
||||
"webhook": {
|
||||
"url": "https://your-webhook-url",
|
||||
"extra_params": {
|
||||
"custom_field": "value"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Via Environment Variables
|
||||
|
||||
```bash
|
||||
WEBHOOK_URL=https://your-webhook-url
|
||||
WEBHOOK_TIMEOUT=30
|
||||
```
|
||||
|
||||
## Example Request
|
||||
|
||||
### ACE Step Text-to-Music Workflow
|
||||
|
||||
```json
|
||||
{
|
||||
"input": {
|
||||
"workflow_json": {
|
||||
"14": {
|
||||
"inputs": {
|
||||
"tags": "funk, pop, upbeat, 105 BPM",
|
||||
"lyrics": "Turn it up and let it flow",
|
||||
"lyrics_strength": 0.99,
|
||||
"clip": ["40", 1]
|
||||
},
|
||||
"class_type": "TextEncodeAceStepAudio"
|
||||
},
|
||||
"17": {
|
||||
"inputs": {
|
||||
"seconds": 180,
|
||||
"batch_size": 1
|
||||
},
|
||||
"class_type": "EmptyAceStepLatentAudio"
|
||||
},
|
||||
"40": {
|
||||
"inputs": {
|
||||
"ckpt_name": "ace_step_v1_3.5b.safetensors"
|
||||
},
|
||||
"class_type": "CheckpointLoaderSimple"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Response Format
|
||||
|
||||
A successful response includes execution metadata, ComfyUI output details, and generated audio assets.
|
||||
|
||||
### Response Fields
|
||||
|
||||
- `id`: Unique request identifier
|
||||
- `status`: `completed`, `failed`, `processing`, `generating`, or `queued`
|
||||
- `message`: Human-readable status message
|
||||
- `comfyui_response`: Raw response from ComfyUI, including execution status and progress
|
||||
- `output`: Array of generated outputs
|
||||
- `timings`: Timing information for the request
|
||||
|
||||
### Output Object
|
||||
|
||||
Each entry in `output` includes:
|
||||
|
||||
- `filename`: Generated file name (e.g., `.mp3`)
|
||||
- `local_path`: File path on the worker
|
||||
- `url`: Pre-signed download URL (if S3 is configured)
|
||||
- `type`: Output type (`output`)
|
||||
- `subfolder`: Output directory (e.g., `audio`)
|
||||
- `node_id`: ComfyUI node that produced the output
|
||||
- `output_type`: Output category (e.g., `audio`)
|
||||
|
||||
## Notes and Limitations
|
||||
|
||||
- Only full ComfyUI workflow JSONs are supported
|
||||
- Concurrent requests are not supported per worker
|
||||
- ACE Step model must be installed before processing requests
|
||||
- Audio generation duration and runtime depend on workflow configuration
|
||||
@@ -0,0 +1,149 @@
|
||||
from vastai import Serverless
|
||||
import asyncio
|
||||
|
||||
|
||||
async def main():
|
||||
async with Serverless() as client:
|
||||
endpoint = await client.get_endpoint(name="my-ace-endpoint")
|
||||
|
||||
# ComfyUI API compatible json workflow for ACE Step
|
||||
workflow = {
|
||||
"14": {
|
||||
"inputs": {
|
||||
"tags": "funk, pop, soul, rock, melodic, guitar, drums, bass, keyboard, percussion, 105 BPM, energetic, upbeat, groovy, vibrant, dynamic",
|
||||
"lyrics": "[verse]\nNeon lights they flicker bright\nCity hums in dead of night\nRhythms pulse through concrete veins\nLost in echoes of refrains\n\n[verse]\nBassline groovin in my chest\nHeartbeats match the citys zest\nElectric whispers fill the air\nSynthesized dreams everywhere\n\n[chorus]\nTurn it up and let it flow\nFeel the fire let it grow\nIn this rhythm we belong\nHear the night sing out our song",
|
||||
"lyrics_strength": 0.99,
|
||||
"clip": ["40", 1]
|
||||
},
|
||||
"class_type": "TextEncodeAceStepAudio",
|
||||
"_meta": {
|
||||
"title": "TextEncodeAceStepAudio"
|
||||
}
|
||||
},
|
||||
"17": {
|
||||
"inputs": {
|
||||
"seconds": 180,
|
||||
"batch_size": 1
|
||||
},
|
||||
"class_type": "EmptyAceStepLatentAudio",
|
||||
"_meta": {
|
||||
"title": "EmptyAceStepLatentAudio"
|
||||
}
|
||||
},
|
||||
"18": {
|
||||
"inputs": {
|
||||
"samples": ["52", 0],
|
||||
"vae": ["40", 2]
|
||||
},
|
||||
"class_type": "VAEDecodeAudio",
|
||||
"_meta": {
|
||||
"title": "VAE Decode Audio"
|
||||
}
|
||||
},
|
||||
"40": {
|
||||
"inputs": {
|
||||
"ckpt_name": "ace_step_v1_3.5b.safetensors"
|
||||
},
|
||||
"class_type": "CheckpointLoaderSimple",
|
||||
"_meta": {
|
||||
"title": "Load Checkpoint"
|
||||
}
|
||||
},
|
||||
"44": {
|
||||
"inputs": {
|
||||
"conditioning": ["14", 0]
|
||||
},
|
||||
"class_type": "ConditioningZeroOut",
|
||||
"_meta": {
|
||||
"title": "ConditioningZeroOut"
|
||||
}
|
||||
},
|
||||
"49": {
|
||||
"inputs": {
|
||||
"model": ["51", 0],
|
||||
"operation": ["50", 0]
|
||||
},
|
||||
"class_type": "LatentApplyOperationCFG",
|
||||
"_meta": {
|
||||
"title": "LatentApplyOperationCFG"
|
||||
}
|
||||
},
|
||||
"50": {
|
||||
"inputs": {
|
||||
"multiplier": 1.15
|
||||
},
|
||||
"class_type": "LatentOperationTonemapReinhard",
|
||||
"_meta": {
|
||||
"title": "LatentOperationTonemapReinhard"
|
||||
}
|
||||
},
|
||||
"51": {
|
||||
"inputs": {
|
||||
"shift": 6,
|
||||
"model": ["40", 0]
|
||||
},
|
||||
"class_type": "ModelSamplingSD3",
|
||||
"_meta": {
|
||||
"title": "ModelSamplingSD3"
|
||||
}
|
||||
},
|
||||
"52": {
|
||||
"inputs": {
|
||||
"seed": "__RANDOM_INT__",
|
||||
"steps": 65,
|
||||
"cfg": 4,
|
||||
"sampler_name": "er_sde",
|
||||
"scheduler": "linear_quadratic",
|
||||
"denoise": 1,
|
||||
"model": ["49", 0],
|
||||
"positive": ["14", 0],
|
||||
"negative": ["44", 0],
|
||||
"latent_image": ["17", 0]
|
||||
},
|
||||
"class_type": "KSampler",
|
||||
"_meta": {
|
||||
"title": "KSampler"
|
||||
}
|
||||
},
|
||||
"59": {
|
||||
"inputs": {
|
||||
"filename_prefix": "audio/ComfyUI",
|
||||
"quality": "V0",
|
||||
"audioUI": "",
|
||||
"audio": ["18", 0]
|
||||
},
|
||||
"class_type": "SaveAudioMP3",
|
||||
"_meta": {
|
||||
"title": "Save Audio (MP3)"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
payload = {
|
||||
"input": {
|
||||
"request_id": "",
|
||||
"workflow_json": workflow,
|
||||
"s3": {
|
||||
"access_key_id": "",
|
||||
"secret_access_key": "",
|
||||
"endpoint_url": "",
|
||||
"bucket_name": "",
|
||||
"region": ""
|
||||
},
|
||||
"webhook": {
|
||||
"url": "",
|
||||
"extra_params": {
|
||||
"user_id": "12345",
|
||||
"project_id": "abc-def"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
response = await endpoint.request("/generate/sync", payload)
|
||||
|
||||
# Response contains status, output, and any errors
|
||||
print(response["response"])
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
This is the base PyWorker for ComfyUI. It provides a unified interface for running any ComfyUI workflow through a proxy-based architecture.
|
||||
|
||||
The cost for each request has a static value of `1`. ComfyUI does not handle concurrent workloads and there is no current provision to load multiple instances of ComfyUI per worker node.
|
||||
The cost for each request has a static value of `100`. ComfyUI does not handle concurrent workloads and there is no current provision to load multiple instances of ComfyUI per worker node.
|
||||
|
||||
## Requirements
|
||||
|
||||
@@ -10,55 +10,6 @@ This worker requires both [ComfyUI](https://github.com/comfyanonymous/ComfyUI) a
|
||||
|
||||
A docker image is provided but you may use any if the above requirements are met.
|
||||
|
||||
## Benchmarking
|
||||
|
||||
### Custom Benchmark Workflows
|
||||
|
||||
You can provide a custom ComfyUI workflow for benchmarking by creating `workers/comfyui-json/misc/benchmark.json`. This allows you to test performance using your preferred models and workflow complexity.
|
||||
|
||||
**Ways to provide the benchmark file:**
|
||||
- Fork this repository and add your `benchmark.json` file
|
||||
- Write the file during worker provisioning (onstart script or setup phase)
|
||||
|
||||
An example file is provided in the repository. To ensure varied generations, use the placeholder `__RANDOM_INT__` in place of static seed values - it will be replaced with a random integer for each benchmark run.
|
||||
|
||||
### Default Benchmark (Fallback)
|
||||
|
||||
If `benchmark.json` is not available, a simple image generation benchmark runs when each worker initializes. This validates GPU performance and helps identify underperforming machines.
|
||||
|
||||
The default benchmark uses Stable Diffusion v1.5 with ComfyUI's standard text-to-image workflow. Configure it using these environment variables:
|
||||
|
||||
| Environment Variable | Default Value | Description |
|
||||
| -------------------- | ------------- | ----------- |
|
||||
| BENCHMARK_TEST_WIDTH | 512 | Image width (pixels) |
|
||||
| BENCHMARK_TEST_HEIGHT | 512 | Image height (pixels) |
|
||||
| BENCHMARK_TEST_STEPS | 20 | Number of denoising steps |
|
||||
|
||||
Each benchmark run uses a random prompt from `misc/test_prompts.txt` and a random seed to ensure consistent GPU load patterns.
|
||||
|
||||
#### Calibrating Fallback Benchmark Duration
|
||||
|
||||
To screen for underperforming hardware, set `BENCHMARK_TEST_STEPS` to match your expected production workflow duration. This allows you to identify machines that won't meet performance requirements.
|
||||
|
||||
**Example:** If your typical workflow should complete in 90 seconds on acceptable hardware:
|
||||
|
||||
```bash
|
||||
# 1. Measure it/sec on your reference machine
|
||||
# RTX 4090 typically achieves ~43 it/sec with SD1.5
|
||||
|
||||
# 2. Calculate required steps
|
||||
# 90 seconds × 43 it/sec = 3870 steps
|
||||
|
||||
# 3. Configure benchmark
|
||||
export BENCHMARK_TEST_STEPS=3870
|
||||
|
||||
# 4. Machines completing significantly slower than 90s indicate hardware issues
|
||||
```
|
||||
|
||||
**Performance expectations:**
|
||||
- Benchmark duration should remain consistent across identical GPU models
|
||||
- Significant variation (>20%) may indicate thermal, power, or configuration issues
|
||||
|
||||
## Endpoint
|
||||
|
||||
The worker provides a single endpoint:
|
||||
@@ -215,7 +166,7 @@ WEBHOOK_TIMEOUT=30 # Webhook timeout in seconds
|
||||
|
||||
## Client Libraries
|
||||
|
||||
See the test client examples for implementation details on how to integrate with the ComfyUI worker.
|
||||
See the client example for implementation details on how to integrate with the ComfyUI worker.
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,77 +0,0 @@
|
||||
# <INFERENCE_SERVER> + <MODEL_NAME> (serverless)
|
||||
|
||||
Run <INFERENCE_SERVER> with our serverless autoscaling infrastructure.
|
||||
|
||||
See the [serverless documentation](https://docs.vast.ai/serverless) and the [Getting Started](https://docs.vast.ai/serverless/getting-started) guide for in-depth details about how to use these templates.
|
||||
|
||||
## Configuration
|
||||
|
||||
Two environment variables are provided to help you configure the <INFERENCE_SERVER> server:
|
||||
|
||||
| Variable | Default Value | Used For |
|
||||
| --- | --- | --- |
|
||||
| `MODEL_NAME` | `<MODEL_NAME>` | The model to load. Also accepts [hf.co/repo/model](#) links |
|
||||
| `<ARGS_VAR>` | `<ARGS_VAL>` | Arguments to pass to the `<ARGS_RECEIVER>` command |
|
||||
|
||||
This template has been configured to work with <MIN_VRAM> VRAM. Setting alternative models and server arguments will change the VRAM requirements. Check model cards and <INFERENCE_SERVER_DOCS> for guidance.
|
||||
|
||||
## Usage
|
||||
|
||||
We have provided a demonstration client to help you implement this template into your own infrastructure
|
||||
|
||||
### Client Setup
|
||||
|
||||
Clone the PyWorker repository to your local machine and install the necessary requirements for running the test client.
|
||||
|
||||
```bash
|
||||
git clone https://github.com/vast-ai/pyworker
|
||||
cd pyworker
|
||||
pip install uv
|
||||
uv venv -p 3.12
|
||||
source .venv/bin/activate
|
||||
uv pip install -r requirements.txt
|
||||
```
|
||||
|
||||
### Completions
|
||||
|
||||
Call to `/v1/completions` with json response
|
||||
|
||||
```bash
|
||||
python -m workers.openai.client -k <API_KEY> -e <ENDPOINT_NAME> --completion --model <MODEL_NAME>
|
||||
```
|
||||
|
||||
### Chat Completion (json)
|
||||
|
||||
Call to `/v1/chat/completions` with json response
|
||||
|
||||
```bash
|
||||
python -m workers.openai.client -k <API_KEY> -e <ENDPOINT_NAME> --chat --model <MODEL_NAME>
|
||||
```
|
||||
|
||||
### Chat Completion (streaming)
|
||||
|
||||
Call to `/v1/chat/completions` with streaming response
|
||||
|
||||
```bash
|
||||
python -m workers.openai.client -k <API_KEY> -e <ENDPOINT_NAME> --chat-stream --model <MODEL_NAME>
|
||||
```
|
||||
|
||||
### Tool Use (json)
|
||||
|
||||
Call to `/v1/chat/completions` with tool and json response.
|
||||
|
||||
This test defines a simple tool which will list the contents of the local pyworker directory. The output is then analysed by the model.
|
||||
|
||||
```bash
|
||||
python -m workers.openai.client -k <API_KEY> -e <ENDPOINT_NAME> --tools --model <MODEL_NAME>
|
||||
```
|
||||
|
||||
### Interactive Chat (streaming)
|
||||
|
||||
Interactive session with calls to `/v1/chat/completions`.
|
||||
|
||||
Type `clear` to clear the chat history or `quit` to exit.
|
||||
|
||||
```bash
|
||||
python -m workers.openai.client -k <API_KEY> -e <ENDPOINT_NAME> --interactive --model <MODEL_NAME>
|
||||
```
|
||||
@@ -0,0 +1,170 @@
|
||||
# ComfyUI Wan 2.2 PyWorker
|
||||
|
||||
This is the PyWorker implementation for running **Wan 2.2 T2V A14B** text-to-video workflows in ComfyUI. It provides a unified interface for executing complete ComfyUI video-generation workflows through a proxy-based architecture and returning generated video assets.
|
||||
|
||||
Each request has a static cost of `100`. ComfyUI does not support concurrent workloads, and there is no provision to run multiple ComfyUI instances per worker node.
|
||||
|
||||
## Requirements
|
||||
|
||||
This worker requires the following components:
|
||||
|
||||
- ComfyUI (https://github.com/comfyanonymous/ComfyUI)
|
||||
- ComfyUI API Wrapper (https://github.com/ai-dock/comfyui-api-wrapper)
|
||||
- Wan 2.2 T2V A14B models and required custom nodes
|
||||
|
||||
A Docker image is provided with all required Wan 2.2 models pre-installed, but any image may be used if the above requirements are met.
|
||||
|
||||
## Endpoint
|
||||
|
||||
The worker exposes a single synchronous endpoint:
|
||||
|
||||
- `/generate/sync`: Processes a complete ComfyUI workflow JSON and generates video output
|
||||
|
||||
## Request Format
|
||||
|
||||
The Wan 2.2 worker **only supports custom workflow mode**. Modifier-based workflows are not supported.
|
||||
|
||||
```json
|
||||
{
|
||||
"input": {
|
||||
"request_id": "uuid-string",
|
||||
"workflow_json": {
|
||||
// Complete ComfyUI Wan 2.2 workflow JSON
|
||||
},
|
||||
"s3": { },
|
||||
"webhook": { }
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Request Fields
|
||||
|
||||
### Required Fields
|
||||
|
||||
- `input`: Container for all request parameters
|
||||
- `input.workflow_json`: Complete ComfyUI workflow graph for Wan 2.2 video generation
|
||||
|
||||
### Optional Fields
|
||||
|
||||
- `input.request_id`: Client-defined request identifier
|
||||
- `input.s3`: S3-compatible storage configuration
|
||||
- `input.webhook`: Webhook configuration for completion notifications
|
||||
|
||||
The special string `"__RANDOM_INT__"` may be used in the workflow JSON and will be replaced with a random integer before submission to ComfyUI.
|
||||
|
||||
## S3 Configuration
|
||||
|
||||
Generated video assets can be automatically uploaded to S3-compatible storage. Configuration can be supplied per request or via environment variables. Request-level values take precedence.
|
||||
|
||||
### Via Request JSON
|
||||
|
||||
```json
|
||||
"s3": {
|
||||
"access_key_id": "your-s3-access-key",
|
||||
"secret_access_key": "your-s3-secret-access-key",
|
||||
"endpoint_url": "https://s3.amazonaws.com",
|
||||
"bucket_name": "your-bucket",
|
||||
"region": "us-east-1"
|
||||
}
|
||||
```
|
||||
|
||||
### Via Environment Variables
|
||||
|
||||
```bash
|
||||
S3_ACCESS_KEY_ID=your-key
|
||||
S3_SECRET_ACCESS_KEY=your-secret
|
||||
S3_BUCKET_NAME=your-bucket
|
||||
S3_ENDPOINT_URL=https://s3.amazonaws.com
|
||||
S3_REGION=us-east-1
|
||||
```
|
||||
|
||||
## Webhook Configuration
|
||||
|
||||
Webhooks are triggered on request completion or failure.
|
||||
|
||||
### Via Request JSON
|
||||
|
||||
```json
|
||||
"webhook": {
|
||||
"url": "https://your-webhook-url",
|
||||
"extra_params": {
|
||||
"custom_field": "value"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Via Environment Variables
|
||||
|
||||
```bash
|
||||
WEBHOOK_URL=https://your-webhook-url
|
||||
WEBHOOK_TIMEOUT=30
|
||||
```
|
||||
|
||||
## Example Request
|
||||
|
||||
### Wan 2.2 Text-to-Video Workflow
|
||||
|
||||
```json
|
||||
{
|
||||
"input": {
|
||||
"workflow_json": {
|
||||
"90": {
|
||||
"inputs": {
|
||||
"clip_name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
|
||||
"type": "wan",
|
||||
"device": "default"
|
||||
},
|
||||
"class_type": "CLIPLoader"
|
||||
},
|
||||
"99": {
|
||||
"inputs": {
|
||||
"text": "A cinematic slow-motion portrait of a woman turning her head",
|
||||
"clip": ["90", 0]
|
||||
},
|
||||
"class_type": "CLIPTextEncode"
|
||||
},
|
||||
"104": {
|
||||
"inputs": {
|
||||
"width": 640,
|
||||
"height": 640,
|
||||
"length": 81,
|
||||
"batch_size": 1
|
||||
},
|
||||
"class_type": "EmptyHunyuanLatentVideo"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Response Format
|
||||
|
||||
A successful response includes execution metadata, ComfyUI output details, and generated video assets.
|
||||
|
||||
### Response Fields
|
||||
|
||||
- `id`: Unique request identifier
|
||||
- `status`: `completed`, `failed`, `processing`, `generating`, or `queued`
|
||||
- `message`: Human-readable status message
|
||||
- `comfyui_response`: Raw response from ComfyUI, including execution status and progress
|
||||
- `output`: Array of generated outputs
|
||||
- `timings`: Timing information for the request
|
||||
|
||||
### Output Object
|
||||
|
||||
Each entry in `output` includes:
|
||||
|
||||
- `filename`: Generated file name (e.g., `.mp4`)
|
||||
- `local_path`: File path on the worker
|
||||
- `url`: Pre-signed download URL (if S3 is configured)
|
||||
- `type`: Output type (`output`)
|
||||
- `subfolder`: Output directory (e.g., `video`)
|
||||
- `node_id`: ComfyUI node that produced the output
|
||||
- `output_type`: Output category (e.g., `images`)
|
||||
|
||||
## Notes and Limitations
|
||||
|
||||
- Only full ComfyUI workflow JSONs are supported
|
||||
- Concurrent requests are not supported per worker
|
||||
- Wan 2.2 models must be installed before processing requests
|
||||
- Video generation workflows may take several minutes depending on resolution, length, and GPU performance
|
||||
@@ -0,0 +1,205 @@
|
||||
from vastai import Serverless
|
||||
import asyncio
|
||||
|
||||
async def main():
|
||||
async with Serverless() as client:
|
||||
endpoint = await client.get_endpoint(name="my-wan-endpoint")
|
||||
|
||||
# ComfyUI API compatible json workflow for Wan 2.2 T2V
|
||||
workflow = {
|
||||
"90": {
|
||||
"inputs": {
|
||||
"clip_name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
|
||||
"type": "wan",
|
||||
"device": "default"
|
||||
},
|
||||
"class_type": "CLIPLoader",
|
||||
"_meta": {
|
||||
"title": "Load CLIP"
|
||||
}
|
||||
},
|
||||
"91": {
|
||||
"inputs": {
|
||||
"text": "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走，裸露，NSFW",
|
||||
"clip": ["90", 0]
|
||||
},
|
||||
"class_type": "CLIPTextEncode",
|
||||
"_meta": {
|
||||
"title": "CLIP Text Encode (Negative Prompt)"
|
||||
}
|
||||
},
|
||||
"92": {
|
||||
"inputs": {
|
||||
"vae_name": "wan_2.1_vae.safetensors"
|
||||
},
|
||||
"class_type": "VAELoader",
|
||||
"_meta": {
|
||||
"title": "Load VAE"
|
||||
}
|
||||
},
|
||||
"93": {
|
||||
"inputs": {
|
||||
"shift": 8.000000000000002,
|
||||
"model": ["101", 0]
|
||||
},
|
||||
"class_type": "ModelSamplingSD3",
|
||||
"_meta": {
|
||||
"title": "ModelSamplingSD3"
|
||||
}
|
||||
},
|
||||
"94": {
|
||||
"inputs": {
|
||||
"shift": 8,
|
||||
"model": ["102", 0]
|
||||
},
|
||||
"class_type": "ModelSamplingSD3",
|
||||
"_meta": {
|
||||
"title": "ModelSamplingSD3"
|
||||
}
|
||||
},
|
||||
"95": {
|
||||
"inputs": {
|
||||
"add_noise": "disable",
|
||||
"noise_seed": 0,
|
||||
"steps": 20,
|
||||
"cfg": 3.5,
|
||||
"sampler_name": "euler",
|
||||
"scheduler": "simple",
|
||||
"start_at_step": 10,
|
||||
"end_at_step": 10000,
|
||||
"return_with_leftover_noise": "disable",
|
||||
"model": ["94", 0],
|
||||
"positive": ["99", 0],
|
||||
"negative": ["91", 0],
|
||||
"latent_image": ["96", 0]
|
||||
},
|
||||
"class_type": "KSamplerAdvanced",
|
||||
"_meta": {
|
||||
"title": "KSampler (Advanced)"
|
||||
}
|
||||
},
|
||||
"96": {
|
||||
"inputs": {
|
||||
"add_noise": "enable",
|
||||
"noise_seed": "__RANDOM_INT__",
|
||||
"steps": 20,
|
||||
"cfg": 3.5,
|
||||
"sampler_name": "euler",
|
||||
"scheduler": "simple",
|
||||
"start_at_step": 0,
|
||||
"end_at_step": 10,
|
||||
"return_with_leftover_noise": "enable",
|
||||
"model": ["93", 0],
|
||||
"positive": ["99", 0],
|
||||
"negative": ["91", 0],
|
||||
"latent_image": ["104", 0]
|
||||
},
|
||||
"class_type": "KSamplerAdvanced",
|
||||
"_meta": {
|
||||
"title": "KSampler (Advanced)"
|
||||
}
|
||||
},
|
||||
"97": {
|
||||
"inputs": {
|
||||
"samples": ["95", 0],
|
||||
"vae": ["92", 0]
|
||||
},
|
||||
"class_type": "VAEDecode",
|
||||
"_meta": {
|
||||
"title": "VAE Decode"
|
||||
}
|
||||
},
|
||||
"98": {
|
||||
"inputs": {
|
||||
"filename_prefix": "video/ComfyUI",
|
||||
"format": "auto",
|
||||
"codec": "auto",
|
||||
"video": ["100", 0]
|
||||
},
|
||||
"class_type": "SaveVideo",
|
||||
"_meta": {
|
||||
"title": "Save Video"
|
||||
}
|
||||
},
|
||||
"99": {
|
||||
"inputs": {
|
||||
"text": "Beautiful young European woman with honey blonde hair gracefully turning her head back over shoulder, gentle smile, bright eyes looking at camera. Hair flowing in slow motion as she turns. Soft natural lighting, clean background, cinematic portrait.",
|
||||
"clip": ["90", 0]
|
||||
},
|
||||
"class_type": "CLIPTextEncode",
|
||||
"_meta": {
|
||||
"title": "CLIP Text Encode (Positive Prompt)"
|
||||
}
|
||||
},
|
||||
"100": {
|
||||
"inputs": {
|
||||
"fps": 16,
|
||||
"images": ["97", 0]
|
||||
},
|
||||
"class_type": "CreateVideo",
|
||||
"_meta": {
|
||||
"title": "Create Video"
|
||||
}
|
||||
},
|
||||
"101": {
|
||||
"inputs": {
|
||||
"unet_name": "wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors",
|
||||
"weight_dtype": "default"
|
||||
},
|
||||
"class_type": "UNETLoader",
|
||||
"_meta": {
|
||||
"title": "Load Diffusion Model"
|
||||
}
|
||||
},
|
||||
"102": {
|
||||
"inputs": {
|
||||
"unet_name": "wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors",
|
||||
"weight_dtype": "default"
|
||||
},
|
||||
"class_type": "UNETLoader",
|
||||
"_meta": {
|
||||
"title": "Load Diffusion Model"
|
||||
}
|
||||
},
|
||||
"104": {
|
||||
"inputs": {
|
||||
"width": 640,
|
||||
"height": 640,
|
||||
"length": 81,
|
||||
"batch_size": 1
|
||||
},
|
||||
"class_type": "EmptyHunyuanLatentVideo",
|
||||
"_meta": {
|
||||
"title": "EmptyHunyuanLatentVideo"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
payload = {
|
||||
"input": {
|
||||
"request_id": "",
|
||||
"workflow_json": workflow,
|
||||
"s3": {
|
||||
"access_key_id": "",
|
||||
"secret_access_key": "",
|
||||
"endpoint_url": "",
|
||||
"bucket_name": "",
|
||||
"region": ""
|
||||
},
|
||||
"webhook": {
|
||||
"url": "",
|
||||
"extra_params": {
|
||||
"user_id": "12345",
|
||||
"project_id": "abc-def"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
response = await endpoint.request("/generate/sync", payload)
|
||||
|
||||
# Response contains status, output, and any errors
|
||||
print(response["response"])
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
Reference in New Issue
Block a user