ComfyUI Node

Recraft V4 Styles

A design-model playground without the design-tool learning curve

By Runware·Created 2 years ago·Updated a day ago· 140
Recraft V4 Styles
  • referenceImages
  • advancedFeatures.watermark.image
  • image
positivePrompt
size1K (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 is the design niche's image model - the closed model that lives on leaderboards and in marketing workflows, known for clean vector-friendly output and strong stylistic range rather than photoreal drama. V4 keeps that identity, and this node drops its "Styles" variant into ComfyUI through Runware's cloud. What you get that you won't from a generic diffusion checkpoint is a model whose whole point is style control: generating in a chosen visual language instead of just reacting to your adjectives.

The style story is the reason to read past the generic-looking input list. styleId is the input that makes this node different - an identifier of a style to apply, the same style system Recraft uses across its product. If you've built or favorited a style in Recraft, its ID plugs in here and the model honors it. settings.styleMatch (default precise) sets how closely the model follows that style, with the tooltip noting it overrides the match value stored on the style itself - set it looser when you want the style as a flavor rather than a straitjacket. And advanced_json is the escape hatch for the deeper design controls, letting you merge settings like a background color or a color palette into the request. If you're the sort who thinks in hex codes, that's your door.

The rest is standard current-gen image generation. positivePrompt is required, sentence-style. referenceImages supplies an image reference. size defaults to 1K (1:1) with preset presets up from there, numberResults gives you variations, and the advancedFeatures.watermark.* group handles stamped watermarks. The safety group and outputFormat/outputQuality (JPG default) round it out. Output: image.

Install

It's one node in the Runware pack, so: ComfyUI Manager → search Runware → install → restart, or clone https://github.com/Runware/ComfyUI-Runware into custom_nodes and pip install -r requirements.txt. Add a Runware API key from the dashboard - Settings → Runware API key, RUNWARE_API_KEY, or runware auth login. No weights download; the generation happens on Runware's backend.

The practical read

Reach for Recraft when the job is design-shaped - logos, illustrations, marketing art, anything where a consistent visual language matters more than photographic realism. The community's honest split is that Recraft-class quality is available locally in open models, but nobody local ships Recraft's style-ID system as a first-class feature; if that system is why you're here, this node is how it gets inside a ComfyUI graph. Per-call cost applies and your prompts transit Runware's cloud and moderation. And a tip: don't expect photorealist drama - that's not this model's lane, and fighting its design-DNA for realism is how people get disappointed.

CategoryRunware/Image/recraft

Inputs (21)

NameTypeDefaultDescription
positivePromptSTRINGText prompt describing elements to include in the generated output.
referenceImagesoptIMAGE
advancedFeatures.watermark.imageoptIMAGE
sizeoptCOMBO1K (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