Skip to main content

​
How to use the API

The ViewComfy Serverless API can be called with a JSON POST request or streaming responses via Server-Sent Events. This second option allows for real-time tracking of the ComfyUI logs. In this guide, we will go over how to call the API with the streaming response. All the code you need to run the API can be found in this GitHub folder (this guide uses the Python example code, you can access the TypeScript example code here. It works in the same way.)
If you want a full guide on how to deploy your own workflow, you can find it here.
After downloading all the files, you can install the dependencies: 
pip install -r requirements.txt

​
1. Getting your API keys

In order to use your API endpoint, you will first need to create your API keys. API Key Button After opening the API key menu from your dashboard, you can copy your “Client ID” and “Client Secret”. Keep them somewhere safe as you will need them to call the API. Client Id and Client Secret

​
2. Extracting your workflow parameters

The first thing to do before setting up the request is to identify the parameters in your workflow. This is done by using workflow_parameters_maker.py to flatten your workflow_api.json. You can run the script directly from your terminal: 
python workflow_parameters_maker.py --workflow_api_path "<Path to your workflow_api.json file>"
The flattened json file should look like this: 
{
    "_3-node-class_type-info": "KSampler",
    "3-inputs-cfg": 6,
    …
    "_6-node-class_type-info": "CLIP Text Encode (Positive Prompt)",
    "6-inputs-clip": [
        "38",
        0
    ],
    "6-inputs-text": "A woman raising her head with hair blowing in the wind",
    …
    "_52-node-class_type-info": "Load Image",
    "52-inputs-image": "<path_to_my_image>",
    …
}
This dictionary contains all the parameters in your workflow. The key for each parameter contains the node id from your workflow_api.json file, whether it is an input, and the parameter’s input name. Keys that start with “_” are just there to give you context on the node corresponding to id, they are not parameters. In this example, the first key-value pair shows that node 3 is the KSampler and that “3-inputs-cfg” sets its corresponding cfg value.

​
3. Updating the script with your parameter

All the code you will need to call the API, parse the results and save the outputs are in main.py and api.py. In most cases, the only file you will need to edit is main.py. This is where you will add the parameters you want to change, your API endpoint, and the directory to save your outputs. The first thing to do is to copy the ViewComfy endpoint, the Client ID and the Client Secret from your dashboard and set them to view_comfy_api_url, client_id and client_secret: 
view_comfy_api_url = "<Your_ViewComfy_endpoint>"
client_id = "<Your_Client_ID>"
client_secret = "<Your_Client_Secret>"
You can then set the parameters using the keys from the json file you created in the previous step. In this example, we will change the prompt and the input image: 
params = {}
params["6-inputs-text"] = "A flamingo dancing on top of a server in a pink universe, masterpiece, best quality, very aesthetic"
params["52-inputs-image"] = open("/home/GitHub/API_tests/input_img.png", "rb")

​
4. Calling the API

Once you are done adding your parameters to main.py, you can call the API by running: 
python main.py
This will send your parameters to api.py where all the functions to call the API and handle the outputs are stored. By default the script runs the “infer_with_logs” function which returns the generation logs from ComfyUI via a streaming response. If you would rather call the API via a standard POST request, you can use “infer” instead, like so: 
  # Call the API and wait for the results
    prompt_result = await infer(api_url=view_comfy_api_url, params=params, override_workflow_api=override_workflow_api)
  # ...
  # prompt_result = await infer_with_logs(
  #     api_url=view_comfy_api_url,
  #     params=params,
  #     logging_callback=logging_callback,
  #     override_workflow_api=override_workflow_api
  # )
The result object returned by the API will contain the workflow outputs as well as the generation details. It is formatted as follows (For the full definition you can refer to “PromptResult” inside api.py.): 
prompt_id (str): Unique identifier for the prompt
status (str): Current status of the prompt execution
completed (bool): Whether the prompt execution is complete
execution_time_seconds (float): Time taken to execute the prompt
prompt (Dict): The original prompt configuration
outputs (List[Dict], optional): List of output file data. Defaults to empty list.

​
5. Advanced Usage: Overwrite the deployed workflow

So far we’ve seen how to make an API request to the workflow you uploaded when deploying. In this section, we will go over how to make a request using a different workflow. This approach will work with any workflow that can run on your deployment, so make sure you have installed all nodes and models you need to run the new workflow. (see the “Deploy your workflow” section for information on how to install new nodes and models to a deployment) The first step is to extract the workflow_api.json file for the new workflow. In this case, I will use this file, which is my Wan 2.1 workflow with the addition of a LoRA. You can then add the path to the new workflow_api.json file to “override_workflow_api”: 
override_workflow_api_path = "<path_to_your_new_workflow_api_file>"
From that point onward, you can follow the steps from the previous section to get the parameters from the workflow and make the API call.

​
Code Examples

⌘I