Recraft V4.1 Pro
The better rendering, at a per-image price
- advancedFeatures.watermark.image
- image
Recraft's Pro tier is the one you pay up for when the deliverable actually matters - a hero visual, a client deck, the image that has to survive being printed or shown in a pitch. Same workflow, same node shape, but the checkpoint is recraft:v4.1-pro@0 and the rendering quality (and the price per image) sits a notch above the base model.
Let me be blunt about when you should not reach for it: if you're iterating on layouts or brainstorming 40 directions, use the plain V4.1 node and burn a few cents on roughs. Pro is for the final pass. It's the same design-first character - typography, flat graphics, brand palettes - just with better detail, cleaner edges, and more reliable text.
How it works
It's the standard Runware image node under the hood: positivePrompt, width, and height go in; the request goes out as taskType: imageInference over REST; the returned image URL becomes a native image (IMAGE) tensor on the output. Wire it to Preview Image or Save Image and you're done.
The inputs you'll actually set:
positivePrompt- style and use-case context beat bare object lists with Recraft. "editorial magazine cover, bold serif masthead, duotone illustration" beats "a bird."width/height- 1024×1024 by default.numberResults- up to 20 seeded variations.outputFormat/outputQuality- JPG/PNG/WEBP and 20–99 compression.
And the Recraft specials in advanced_json: settings.backgroundColor.rgb for a background color and settings.colors for a brand palette to generate within.
Output: image (IMAGE).
Installing
One install for the whole pack: ComfyUI Manager → search Runware → install → restart. Manual:
cd ComfyUI/custom_nodes
git clone https://github.com/Runware/ComfyUI-Runware
pip install -r ComfyUI-Runware/requirements.txt
No model downloads, light Python deps (runware-sdk, Pillow). You need a Runware API key from the dashboard, via ComfyUI Settings → Runware API key, RUNWARE_API_KEY, or runware auth login.
Gotchas
The cost gap between base and Pro is real and it's the whole point of the tier - check the per-run cost on the node title bar before you set numberResults to 20 and queue. And remember the Pro/Utility split: Pro is the quality lane, Utility (V4.1 Utility / Utility Pro) is the pragmatic one for product mockups and UI assets. If you keep reaching for Pro and feeling like you're overpaying for flat graphics, you probably want Utility. If the design is the thing being sold, Pro is where the money buys something visible.
Inputs (18)
| Name | Type | Default | Description |
|---|---|---|---|
| positivePrompt | STRING | Text prompt describing elements to include in the generated output. | |
| advancedFeatures.watermark.imageopt | IMAGE | — | |
| sizeopt | COMBO | 2K (1:1) | Output size. Only one of resolution or dimensions is sent. |
| numberResultsopt | INT | 11–20 | Number of results to generate. Each result uses a different seed, producing variations of the same parameters. |
| advancedFeaturesopt | BOOLEAN | false | Enable to set advancedFeatures. Off uses the model's default. |
| advancedFeatures.watermark.bgColoropt | STRING | Background color in hex format. | |
| advancedFeatures.watermark.displayPositionopt | COMBO | (default) | Watermark position. |
| advancedFeatures.watermark.fontColoropt | STRING | Text color in hex format. | |
| advancedFeatures.watermark.opacityopt | BOOLEAN | false | Enable to set advancedFeatures.watermark.opacity. Off uses the model's default. |
| advancedFeatures.watermark.opacity_valueopt | FLOAT | 0.100.1–1 | Watermark opacity. |
| advancedFeatures.watermark.textopt | STRING | Watermark text. | |
| safetyopt | BOOLEAN | false | Enable to set safety. Off uses the model's default. |
| safety.checkContentopt | BOOLEAN | false | Enable or disable content safety checking. |
| ttlopt | BOOLEAN | false | Enable to set ttl. Off uses the model's default. |
| ttl_valueopt | INT | 60 | Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`. |
| outputFormatopt | COMBO | JPG | File format for the generated image. |
| outputQualityopt | INT | 9520–99 | Compression quality of the output. Higher values preserve quality but increase file size. |
| advanced_jsonopt | STRING | Optional JSON merged into the request. For: settings.backgroundColor.rgb, settings.colors |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |