Last Updated: July 9, 2025
Deploy from the SaladCloud Portal.

​
Overview

Inference is powered by ComfyUI, exposed via ComfyUI API to facilitate horizontally scalable operation. Users can make an HTTP request to the provided endpoints and get back one or more outputs in base64 encoded form, via Webhook, or via S3. THIS RECIPE DOES NOT SERVE THE WEB UI. Several models are available, including: Don’t see the model you want? It’s easy to customize this recipe to run any ComfyUI workflow. Check out the example Docker images to see how it’s done.

​
Example request

Submit API-formatted ComfyUI prompts to the /prompt endpoint, and receive base64-encoded images in response. 
curl -X POST https://vegetable-words-3e487ysdyhfkvjah.salad.cloud/prompt \
-H "Content-Type: application/json" \
-H "Salad-Api-Key: <YOUR_API_KEY>" \
-d @prompt.json \
| jq -r .images[0] | base64 --decode > output.jpg
prompt.json
{
  "prompt": {
    "6": {
      "inputs": {
        "text": "leafy green spaceship descending from orbit into a lush bio-organic cityscape. the sky is pale purple, and red storm clouds form in the distance, crackling with lightning.",
        "clip": ["30", 1]
      },
      "class_type": "CLIPTextEncode",
      "_meta": {
        "title": "CLIP Text Encode (Positive Prompt)"
      }
    },
    "8": {
      "inputs": {
        "samples": ["31", 0],
        "vae": ["30", 2]
      },
      "class_type": "VAEDecode",
      "_meta": {
        "title": "VAE Decode"
      }
    },
    "9": {
      "inputs": {
        "filename_prefix": "ComfyUI",
        "images": ["8", 0]
      },
      "class_type": "SaveImage",
      "_meta": {
        "title": "Save Image"
      }
    },
    "27": {
      "inputs": {
        "width": 1024,
        "height": 1024,
        "batch_size": 1
      },
      "class_type": "EmptySD3LatentImage",
      "_meta": {
        "title": "EmptySD3LatentImage"
      }
    },
    "30": {
      "inputs": {
        "ckpt_name": "flux1-dev-fp8.safetensors"
      },
      "class_type": "CheckpointLoaderSimple",
      "_meta": {
        "title": "Load Checkpoint"
      }
    },
    "31": {
      "inputs": {
        "seed": 793373912447585,
        "steps": 20,
        "cfg": 1,
        "sampler_name": "euler",
        "scheduler": "simple",
        "denoise": 1,
        "model": ["30", 0],
        "positive": ["35", 0],
        "negative": ["33", 0],
        "latent_image": ["27", 0]
      },
      "class_type": "KSampler",
      "_meta": {
        "title": "KSampler"
      }
    },
    "33": {
      "inputs": {
        "text": "",
        "clip": ["30", 1]
      },
      "class_type": "CLIPTextEncode",
      "_meta": {
        "title": "CLIP Text Encode (Negative Prompt)"
      }
    },
    "35": {
      "inputs": {
        "guidance": 3.5,
        "conditioning": ["6", 0]
      },
      "class_type": "FluxGuidance",
      "_meta": {
        "title": "FluxGuidance"
      }
    }
  },
  "webhook": "https://example.com/webhook",
  "convert_output": {
    "format": "jpeg",
    "options": {
      "quality": 80,
      "progressive": true
    }
  }
}
You will get back a json response with the base64-encoded image data, which you can decode and save to a file. 
{
  "id": "1234567890abcdef",
  "prompt": ...,
  "images": ["base64-encoded-image-data"]
}

​
How To Use This Recipe

​
Authentication

When deploying this recipe, you can optionally enable authentication in the container gateway. If you enable authentication, all requests to your API will need to include your SaladCloud API key in the header Salad-Api-Key. See the documentation for more information about authentication.

​
Replica Count

The recipe is configured for 3 replicas by default, and we recommend using at least 3 for testing, and at least 5 for production workloads. SaladCloud’s distributed GPU cloud is powered by idle gaming PCs around the world, in private residences, gaming cafes, and esports arenas. A consequence of this unique infrastructure is that all nodes must be considered interruptible without warning. If a 👨‍🍳 Chef (a compute host) decides they want to use their GPU to play a video game, or their dog trips on the power cord, or their Wi-Fi goes out, the instance of your workload running on that node will be interrupted, and a new instance will be allocated to a different node. This means you may want to slightly over-provision the capacity you expect to need in order to have adequate coverage during node reallocations. Don’t worry, we only charge for instances that are actually running.

​
Logging

SaladCloud offers a simple built-in method to view logs from the portal, to facilitate testing and development. For production workloads, we highly recommend connecting an external logging source, such as Axiom. This can be done during container group creation.

​
Deploy It And Wait

When you deploy the recipe, SaladCloud will find the desired number of qualified nodes, and begin the process of downloading the container image to the host machine. Depending on the model you choose, the image can be anywhere from 6GB for Dreamshaper 8, up to 16GB for the Flux models, and it may take up to tens of minutes to download to some machines, depending on the network conditions of that particular node. Remember, these are residential PCs with residential internet connections, and performance will vary across different nodes. Eventually, you will see instances enter the running state, and show a green checkmark in the “Ready” column, indicating the workload is passing its readiness probe. Once at least 1 instance is running, the container group will be considered running, but for production you will want to wait until an adequate number of nodes have become ready before moving traffic over. You will find helpful links and information in the readme on the container group page once deployed.

​
Source Code

Github Repository