Platform For AI:AI video generation - ComfyUI deployment

Online debugging

On the Elastic Algorithm Service (EAS) page, find the target service and click Online Debugging in the Actions column.

1. Send a POST request to obtain a Prompt ID.

   1. On the debug page, in the Online Debugging Request Parameters section, enter the request body in the Body field. Then, add /prompt to the request URL text box.

   2. Click Send Request to view the response in the Debugging Information area, as shown in the following figure.

2. Send a GET request to retrieve the inference result based on the Prompt ID.

   1. In the Online API Debugging Request Parameters area, set the request method to GET and enter /history/<prompt id> in the text box, as shown in the following figure.

      Replace <prompt id> with the Prompt ID that you obtained in the previous step.

   2. Click Send Request to obtain the inference result.

      You can view the generated inference result in the output directory of the mounted storage.

Synchronous call

1. View the endpoint information.

   1. On the Inference Service tab, click your service name to go to the Overview page. In the Basic Information section, click View Endpoint Information.

   2. In the Invocation Method panel, you can obtain the endpoint and token. Select an Internet or VPC endpoint as needed. This topic uses <EAS_ENDPOINT> and <EAS_TOKEN> to represent the endpoint and token, respectively.

      

2. Send a POST request to obtain a Prompt ID.

   • HTTP request method: POST.

   • URI of the request (URL): <EAS_ENDPOINT>/prompt. If <EAS_ENDPOINT> ends with a forward slash (/), delete it. The final URL should look similar to this example: http://comfyui****.175805416243****.cn-beijing.pai-eas.aliyuncs.com/prompt.

   • Request header (Headers):

     Header	Value	Description
     Authorization	<EAS_TOKEN>	The licensing key.
     Content-Type	application/json	Specifies the format of the request body.

   Sample code:

   cURL

   curl --location --request POST '<EAS_ENDPOINT>/prompt' \
   --header 'Authorization: <EAS_TOKEN>' \
   --header 'Content-Type: application/json' \
   --data-raw '{
       "prompt":
       ...omitted
   }'

   In this case, --data-raw is the request body.

   Python

   Sample code:

   import requests
   import json
   
   # Replace <EAS_ENDPOINT> and <EAS_TOKEN> with the endpoint and token obtained in Step 1.
   service_url = "<EAS_ENDPOINT>"
   token = "<EAS_TOKEN>"
   
   if service_url[-1] == "/":
       service_url = service_url[:-1]
   
   # Request body. Configure the value of prompt in the payload as the content of the JSON file corresponding to the workflow.
   payload = """{
       "prompt":
       ...omitted
   }"""
   payload = json.loads(payload)
   
   session = requests.session()
   session.headers.update({"Authorization": token})
     
   response = session.post(url=f'{service_url}/prompt', json=payload)
   if response.status_code != 200:
       raise Exception(response.content)
   
   data = response.json()
   print(data)

   Sample response:

   {
       "prompt_id": "021ebc5b-e245-4e37-8bd3-00f7b949****",
       "number": 5,
       "node_errors": {}
   }

   You can obtain the Prompt ID from the returned result.

3. Send a request to obtain the inference result.

   • HTTP request method: GET

   • Request URL: <EAS_ENDPOINT>/history/<prompt_id>. Replace <prompt_id> with the prompt_id obtained in the previous step.

   • Request header:

     Header	Value	Description
     Authorization	<EAS_TOKEN>	The licensing key, which is obtained in Step 1.

   Sample code:

   cURL

   curl --location --request GET '<EAS_ENDPOINT>/history/<prompt_id>' \
        --header 'Authorization: <EAS_TOKEN>'

   Python

   import requests
   
   # Replace <EAS_ENDPOINT> and <EAS_TOKEN> with the endpoint and token obtained in Step 1.
   # Replace <prompt_id> with the prompt_id obtained in Step 2.
   service_url = "<EAS_ENDPOINT>"
   token = "<EAS_TOKEN>"
   prompt_id = "<prompt_id>"
   
   if service_url[-1] == "/":
       service_url = service_url[:-1]
   
   session = requests.session()
   session.headers.update({"Authorization": token})
   
   response = session.get(url=f'{service_url}/history/{prompt_id}')
   
   if response.status_code != 200:
       raise Exception(response.content)
   
   data = response.json()
   print(data)

   Sample response:

   Click to view a sample response

   {
       "130bcd6b-5bb5-496c-9c8c-3a1359a0****": {
           "prompt": ...omitted,
           "outputs": {
               "9": {
                   "images": [
                       {
                           "filename": "ComfyUI_1712645398_18dba34d-df87-4735-a577-c63d5506a6a1_.png",
                           "subfolder": "",
                           "type": "output"
                       }
                   ]
               },
               "15": {
                   "images": [
                       {
                           "filename": "ComfyUI_1712645867_.webp",
                           "subfolder": "",
                           "type": "output"
                       }
                   ],
                   "animated": [
                       true
                   ]
               },
               "19": {
                   "gifs": [
                       {
                           "filename": "comfyUI_00002.mp4",
                           "subfolder": "",
                           "type": "output",
                           "format": "video/h264-mp4"
                       }
                   ]
               }
           },
           "status": {
               "status_str": "success",
               "completed": true,
               "messages": ...omitted,
           }
       }
   }
   

   The outputs in this sample response provides the image, webp file, and mp4 video generated by the prompt. You can find these files by file name in the output directory of the mounted storage.

Asynchronous invocation

1. On the Inference Service tab, click the target service name to open the Overview page. In the Basic Information section, click View Invocation Information. In the Invocation Information dialog box, on the Asynchronous Invocation tab, you can view the service endpoint and token.

   

2. Push a request.

   Sample code:

   import requests,io,base64
   from PIL import Image, PngImagePlugin
   import json
   
   service_url = "<EAS_ENDPOINT>"
   token = "<EAS_TOKEN>"
   
   if service_url[-1] == "/":
       service_url = service_url[:-1]
   
   session = requests.session()
   session.headers.update({"Authorization":token})
   
   # Request body, which is the content of the workflow JSON file. Use """ """ to define it as a multi-line string. Otherwise, you need to capitalize the first letter of the Boolean values (true and false) in the workflow JSON.
   payload = """{
       '3': 
       ...omitted
     }
     """
   payload = json.loads(payload)
   
   for i in range(5):
     # task_id is a key flag to identify the request and result. Assign a unique value to each request to correspond to the subsequent queue result.
     response = session.post(url=f'{service_url}/api_prompt?task_id=txt2img_{i}', json=payload)
     if response.status_code != 200:
       exit(f"send request error:{response.content}")
     else:
       print(f"send {i} success, index is {response.content}")

3. Subscribe to results.

   1. Run the following command to install the eas_prediction SDK.

      pip install eas_prediction  --user

   2. Run the following code to obtain the returned result.

      from eas_prediction import QueueClient
      from urllib.parse import urlparse, urlunparse
      
      service_url     = "<EAS_ENDPOINT>"
      token           = "<EAS_TOKEN>"
      
      def parse_service_url(service_url):
          parsed = urlparse(service_url)
          service_domain = f"{parsed.scheme}://{parsed.netloc}"
          path_parts = [p for p in parsed.path.strip('/').split('/') if p]
          service_name = path_parts[-1]
          return service_domain, service_name
      
      service_domain, service_name = parse_service_url(service_url)
      print(f"service_domain: {service_domain}, service_name: {service_name}.")
          
      sink_queue = QueueClient(service_domain, f'{service_name}/sink')
      sink_queue.set_token(token)
      sink_queue.init()
      
      watcher = sink_queue.watch(0, 5, auto_commit=False)
      for x in watcher.run():
          if 'task_id' in x.tags:
              print('index {} task_id is {}'.format(x.index, x.tags['task_id']))
          print(f'index {x.index} data is {x.data}')
          sink_queue.commit(x.index)

      Sample response:

      index 42 task_id is txt2img_0
      index 42 data is b'[{"type": "executed", "data": {"node": "9", "output": {"images": [{"filename": "ComfyUI_1712647318_8e7f3c93-d2a8-4377-92d5-8eb552adc172_.png", "subfolder": "", "type": "output"}]}, "prompt_id": "c3c983b6-f92b-4dd5-b4dc-442db4d1736f"}}, {"type": "executed", "data": {"node": "15", "output": {"images": [{"filename": "ComfyUI_1712647895_.webp", "subfolder": "", "type": "output"}], "animated": [true]}, "prompt_id": "c3c983b6-f92b-4dd5-b4dc-442db4d1736f"}}, {"type": "executed", "data": {"node": "19", "output": {"gifs": [{"filename": "comfyUI_00001.mp4", "subfolder": "", "type": "output", "format": "video/h264-mp4"}]}, "prompt_id": "c3c983b6-f92b-4dd5-b4dc-442db4d1736f"}}, {"9": {"images": [{"filename": "ComfyUI_1712647318_8e7f3c93-d2a8-4377-92d5-8eb552adc172_.png", "subfolder": "", "type": "output"}]}, "15": {"images": [{"filename": "ComfyUI_1712647895_.webp", "subfolder": "", "type": "output"}], "animated": [true]}, "19": {"gifs": [{"filename": "comfyUI_00001.mp4", "subfolder": "", "type": "output", "format": "video/h264-mp4"}]}}]'
      index 43 task_id is txt2img_1
      index 43 data is b'[{"9": {"images": [{"filename": "ComfyUI_1712647318_8e7f3c93-d2a8-4377-92d5-8eb552adc172_.png", "subfolder": "", "type": "output"}]}, "15": {"images": [{"filename": "ComfyUI_1712647895_.webp", "subfolder": "", "type": "output"}], "animated": [true]}, "19": {"gifs": [{"filename": "comfyUI_00001.mp4", "subfolder": "", "type": "output", "format": "video/h264-mp4"}]}}]'
      index 44 task_id is txt2img_2
      index 44 data is b'[{"9": {"images": [{"filename": "ComfyUI_1712647318_8e7f3c93-d2a8-4377-92d5-8eb552adc172_.png", "subfolder": "", "type": "output"}]}, "15": {"images": [{"filename": "ComfyUI_1712647895_.webp", "subfolder": "", "type": "output"}], "animated": [true]}, "19": {"gifs": [{"filename": "comfyUI_00001.mp4", "subfolder": "", "type": "output", "format": "video/h264-mp4"}]}}]'
      index 45 task_id is txt2img_3
      index 45 data is b'[{"9": {"images": [{"filename": "ComfyUI_1712647318_8e7f3c93-d2a8-4377-92d5-8eb552adc172_.png", "subfolder": "", "type": "output"}]}, "15": {"images": [{"filename": "ComfyUI_1712647895_.webp", "subfolder": "", "type": "output"}], "animated": [true]}, "19": {"gifs": [{"filename": "comfyUI_00001.mp4", "subfolder": "", "type": "output", "format": "video/h264-mp4"}]}}]'
      index 46 task_id is txt2img_4
      index 46 data is b'[{"9": {"images": [{"filename": "ComfyUI_1712647318_8e7f3c93-d2a8-4377-92d5-8eb552adc172_.png", "subfolder": "", "type": "output"}]}, "15": {"images": [{"filename": "ComfyUI_1712647895_.webp", "subfolder": "", "type": "output"}], "animated": [true]}, "19": {"gifs": [{"filename": "comfyUI_00001.mp4", "subfolder": "", "type": "output", "format": "video/h264-mp4"}]}}]'

      You can view the inference result files in the output directory of the mounted storage.