ComfyUI Node

Recraft V4.1

The refresh, and when it's actually worth it

By Runware·Created 2 years ago·Updated about a month ago· 140
Recraft V4.1
  • advancedFeatures.watermark.image
  • image
positivePrompt
size1K (1:1)
numberResults1
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
ttlfalse
ttl_value60
outputFormatJPG
outputQuality95
advanced_json

Recraft V4.1 is the incremental refresh of the design-first image model, and in ComfyUI it looks almost exactly like its predecessor - same inputs, same IMAGE output, same cloud-rendered workflow. This node is the one to reach for if you're starting a new project today and your deliverable is a graphic: poster, logo direction, editorial layout, packaging, anything where strong typography and flat style matter more than "photorealistic woman at golden hour."

Why prefer 4.1 over plain V4? It's the newer checkpoint, so it's the one Recraft is actively improving and the one new workflows should target. The practical differences between the point releases are mostly in the rendering details - better text handling, cleaner vector-adjacent output - which is exactly the axis this model competes on. If an old workflow references V4 and still works, leave it alone; if you're building fresh, use 4.1.

How it works

Mechanically it's the standard Runware image node: positivePrompt, width, and height go in, the pack sends recraft:v4.1@0 with taskType: imageInference to Runware's API, and the result comes back as a native image (IMAGE) tensor you can wire into Preview Image or Save Image.

The inputs that matter:

  • positivePrompt - say what the graphic is and in what style. Recraft responds well to design context: "icon set, flat vector, consistent stroke width, pastel palette."
  • width / height - default 1024×1024.
  • numberResults - up to 20 seeded variations in one queue.
  • outputFormat (JPG/PNG/WEBP) and outputQuality.

Then the Recraft specials: advanced_json accepts settings.backgroundColor.rgb and settings.colors - a background color and a brand palette the model works within. Note the JSON path changed from V4's providerSettings.recraft.* to a flatter settings.*; don't copy old JSON verbatim.

Installing

Pack-wide, one install: ComfyUI Manager → Custom Nodes Manager → search Runware → install → restart. Manual alternative:

cd ComfyUI/custom_nodes
git clone https://github.com/Runware/ComfyUI-Runware
pip install -r ComfyUI-Runware/requirements.txt

Light dependencies (runware-sdk, Pillow, soundfile), zero model downloads - the model is hosted. You still need a Runware API key from the dashboard, set in ComfyUI Settings, as RUNWARE_API_KEY, or via runware auth login.

Gotchas

The honest advice: don't agonize over V4 vs 4.1. They're close enough that your prompt and palette matter more than the point release. What does vary is the tier - the base 4.1 is the generalist, Pro is the higher-quality/more-expensive lane, Utility is the boring-but-reliable graphics workhorse. If this node feels underwhelming, that's usually a prompt problem (too vague about style) or you actually wanted a Pro/Utility variant. And remember each numberResults is a paid call - the node's title bar shows cost per run, so keep an eye on it before you batch 20.

CategoryRunware/Image/recraft

Inputs (18)

NameTypeDefaultDescription
positivePromptSTRINGText prompt describing elements to include in the generated output.
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.
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.
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