Does this workflow work for portraits or only landscapes?

It will run on any photo, but the enhancement is tuned for natural scenery (foliage, rocks, skies). For portraits, consider a portrait-optimized model or a portrait-focused workflow.

How large can I upscale before running into GPU memory limits?

That depends on your VRAM and the input size. Start with 2x in ImageScaleBy and check the target size from GetImageSize. If you hit memory errors, try a smaller scale or process smaller crops.

Where are my outputs saved?

By default, SaveImage writes to the ComfyUI/output folder. You can change the filename or directory in the SaveImage node settings before running.

Will enhancement change colors or add artifacts?

TopazImageEnhanceV2 aims to preserve color while restoring detail. Minor shifts or halos can occur with aggressive settings—dial back enhancement or use a smaller scale and re-run. You can also do final color adjustments in your editor if needed.

Image Upscale: Topaz Reimagine Landscape

This ComfyUI tutorial workflow upscales a landscape photo and restores fine natural detail using the TopazImageEnhanceV2 node. It starts with LoadImage, reads the original dimensions via GetImageSize, and scales the image with ImageScaleBy to your chosen factor (for example, 2x or 4x). The upscaled image is then passed to TopazImageEnhanceV2 (Topaz model) to bring back foliage texture, rock edges, and sky gradients while controlling noise and softness. Finally, SaveImage writes the enhanced output, and ImageCompare helps you visually inspect before/after results side-by-side.

Technically, the pipeline separates geometric upscaling from semantic enhancement. ImageScaleBy handles precise resizing based on the dimensions reported by GetImageSize, while TopazImageEnhanceV2 applies learned restoration tuned for natural scenery. The "Upscale Setting" group exposes the key controls so you can quickly adjust scale and enhancement behavior for different landscape inputs. This makes it a practical go-to for turning good scenic shots into print-ready or high-resolution web assets without over-sharpening or plastic artifacts.

API

Use this workflow from code

Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.

c1c683b83324.json

Fetching workflow JSON…

Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.

// Install (beta)
npm i @comfyorg/sdk

// Run this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";

const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");

The SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).

Comfy Cloud API access requires a plan with an API key.

SDK docs Get an API key

FAQ

Frequently Asked Questions