HitPaw: Portrait Diffusion Upscaler

Upload a low-quality portrait image and adjust the upscaling factor. Generate a high-fidelity, detailed portrait with enhanced skin textures and facial features.

Download Workflow Try in Cloud

About

This ComfyUI workflow, titled 'HitPaw: Portrait Diffusion Upscaler,' is designed to enhance low-quality portrait images by increasing their resolution and improving detail. The workflow leverages the HitPawGeneralImageEnhance model, which specializes in refining skin textures and facial features, resulting in high-fidelity portraits.

The process begins with the LoadImage node, where users upload their low-quality images. The core of the enhancement is handled by the HitPawGeneralImageEnhance node, which applies sophisticated diffusion techniques to upscale the image while preserving and enhancing crucial details. Finally, the SaveImage node allows users to save the enhanced image for further use.

Technically, this workflow utilizes a combination of nodes that streamline the image enhancement process. The LoadImage node imports the image into the workflow, while the HitPawGeneralImageEnhance node performs the heavy lifting by applying advanced AI algorithms to upscale the image. The ImageCompare node is available under Nodes 2.0, providing users with a side-by-side comparison of the original and enhanced images, ensuring the improvements are visually evident.

This workflow is particularly useful for photographers, graphic designers, and social media influencers who need to enhance portrait images without losing quality.

What you provide

Reading the workflow

Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.

Try in Cloud

Output

Use this workflow from code

Generated from the workflow graph and inputs when possible; stored examples are shown otherwise. Review credentials and endpoints before running code, which may incur charges.

Get API key

What you need

Runs on: Comfy Cloud
Key: COMFY_API_KEY

Needs a paid Cloud plan and credits.

Download API JSON

# Python 3.10+: pip install comfy-sdk==0.4.0
import os

from comfy_sdk import Comfy

api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
    "2": {
        "class_type": "LoadImage",
        "inputs": {
            "image": "sunlit_girl_portrait.png"
        },
        "_meta": {
            "title": "Load Image"
        }
    },
    "3": {
        "class_type": "SaveImage",
        "inputs": {
            "filename_prefix": "ComfyUI",
            "images": [
                "11",
                0
            ]
        },
        "_meta": {
            "title": "Save Image"
        }
    },
    "4": {
        "class_type": "ImageCompare",
        "inputs": {
            "compare_view": {
                "__value__": [
                    "",
                    ""
                ]
            },
            "image_a": [
                "2",
                0
            ],
            "image_b": [
                "11",
                0
            ]
        },
        "_meta": {
            "title": "Compare Images"
        }
    },
    "11": {
        "class_type": "HitPawGeneralImageEnhance",
        "inputs": {
            "auto_downscale": True,
            "image": [
                "2",
                0
            ],
            "model": "generative_portrait",
            "upscale_factor": 1
        },
        "_meta": {
            "title": "HitPaw General Image Enhance"
        }
    }
})

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)

API documentation

HitPaw: Portrait Diffusion Upscaler

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

Can this workflow be used on non-portrait images?

What is the recommended upscaling factor for best results?

Do I need any special hardware to run this workflow?

How can I compare the original and enhanced images?