ComfyUI Node

Recraft V4 Styles Pro

The bigger-render tier of the style engine

By Runware·Created 2 years ago·Updated a day ago· 140
Recraft V4 Styles Pro
  • referenceImages
  • advancedFeatures.watermark.image
  • image
positivePrompt
size2K (1:1)
numberResults1
styleId
advancedFeaturesfalse
advancedFeatures.watermark.bgColor
advancedFeatures.watermark.displayPosition(default)
advancedFeatures.watermark.fontColor
advancedFeatures.watermark.opacityfalse
advancedFeatures.watermark.opacity_value0.10
advancedFeatures.watermark.text
safetyfalse
safety.checkContentfalse
settings.styleMatchprecise
ttlfalse
ttl_value60
outputFormatJPG
outputQuality95
advanced_json

Recraft V4 Styles Pro is the higher-render tier of Recraft's style-driven image model, and the honest summary is in the default: where the base V4 Styles node starts at 1K, this one starts at 2K (1:1). Pro is Recraft's "the deliverable matters" lane - bigger output, presumably more of the model's quality budget behind it, and the same style-control system that makes the Recraft family distinct. If you've read the base V4 Styles page, the input list is a near-copy, because tiered model nodes share a canvas on purpose: build once, swap the node when a design needs the bigger treatment.

The style machinery carries over unchanged, and it's still the reason to pick Recraft over a generic checkpoint. styleId takes an identifier from Recraft's style system - a style you built or favorited - and applies it to the generation. settings.styleMatch (default precise) governs how closely the model follows that style, overriding whatever match value the style itself stores; dial it looser when you want a flavor rather than a faithful execution. referenceImages supplies a visual reference, and advanced_json remains the escape hatch for design parameters the widgets don't surface, like background color or a specific color palette. positivePrompt is required and sentence-style; numberResults gives variations; the advancedFeatures.watermark.* group stamps watermarks if your use case demands it; safety, outputFormat (JPG default) and outputQuality close it out. Output is image.

Install

The one-time Runware pack setup applies to every node in it, this one included: ComfyUI Manager → search Runware → install → restart, or cd ComfyUI/custom_nodes && git clone https://github.com/Runware/ComfyUI-Runware && pip install -r ComfyUI-Runware/requirements.txt. Then a Runware API key from the dashboard - Settings → Runware API key, RUNWARE_API_KEY, or runware auth login. No checkpoints download; the model lives server-side.

Picking the tier

This is a workflow-discipline question more than a technical one. Draft and iterate on the base V4 Styles node at 1K, and only promote to Pro for the renders that ship - posters, hero assets, anything a client or a sign-off will look at closely, where the 2K baseline and the premium model tier buy you headroom. Watch the per-run cost printed on the node's title bar so the upgrade is a decision, not a surprise. Same standing caveats as the rest of the pack: it's a closed hosted model, so per-call billing, your prompts transit Runware's cloud and moderation, and there's no local fallback for the Recraft style-ID system.

CategoryRunware/Image/recraft

Inputs (21)

NameTypeDefaultDescription
positivePromptSTRINGText prompt describing elements to include in the generated output.
referenceImagesoptIMAGE
advancedFeatures.watermark.imageoptIMAGE
sizeoptCOMBO2K (1:1)Output size. Only one of resolution or dimensions is sent.
numberResultsoptINT11–20Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
styleIdoptSTRINGIdentifier of an existing style to apply.
advancedFeaturesoptBOOLEANfalseEnable to set advancedFeatures. Off uses the model's default.
advancedFeatures.watermark.bgColoroptSTRINGBackground color in hex format.
advancedFeatures.watermark.displayPositionoptCOMBO(default)Watermark position.
advancedFeatures.watermark.fontColoroptSTRINGText color in hex format.
advancedFeatures.watermark.opacityoptBOOLEANfalseEnable to set advancedFeatures.watermark.opacity. Off uses the model's default.
advancedFeatures.watermark.opacity_valueoptFLOAT0.100.1–1Watermark opacity.
advancedFeatures.watermark.textoptSTRINGWatermark text.
safetyoptBOOLEANfalseEnable to set safety. Off uses the model's default.
safety.checkContentoptBOOLEANfalseEnable or disable content safety checking. Increases total generation time.
settings.styleMatchoptCOMBOpreciseHow closely the style is followed. Overrides the match value stored on the style for this request.
ttloptBOOLEANfalseEnable to set ttl. Off uses the model's default.
ttl_valueoptINT60Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.
outputFormatoptCOMBOJPGFile format for the generated image.
outputQualityoptINT9520–99Compression quality of the output. Higher values preserve quality but increase file size.
advanced_jsonoptSTRINGOptional JSON merged into the request. For: settings.backgroundColor.rgb, settings.colors

Outputs (1)

NameTypeDescription
imageIMAGE