ImagineArt 1.5
The cheap-and-cheerful text-to-image node
- advancedFeatures.watermark.image
- image
Sometimes you don't need a 9-billion-parameter masterpiece, you need a lot of images for almost nothing. ImagineArt 1.5 is Runware's own workhorse text-to-image model, and it's the node you reach for when you want to iterate fast on a budget. It's one of the simplest nodes in the whole pack - prompt in, IMAGE out, no model files, no VRAM math.
ImagineArt is Runware's in-house model family (the imagine.art consumer product runs on it), and in the ComfyUI pack it lives under Runware/Image/imagineart as a plain txt2img node. If you're prototyping composition, testing prompt phrasings, or generating a batch of concept thumbnails, this is the cheap lane.
How it works
The only required input is positivePrompt. Everything else is optional:
width/height- default 1024². Set to your target aspect.numberResults- 1 to 20, each on a different seed. This is where the value lives: this model is cheap enough that rolling 8 variations of a prompt costs pocket change, and you pick the winner instead of re-running.safety.checkContent- opt into the moderation pass; results show asNSFW: yes/noin the node's title bar.outputFormat/outputQuality- JPG/PNG/WEBP and compression level. Leave alone unless you have a reason.
The output is a native IMAGE, so it wires straight into Preview Image or Save Image. The request runs on Runware's cloud via the runware-sdk and comes back decoded into the same tensor type ComfyUI expects - you never touch a URL or a file path.
There's no seed widget on this node (that's a 2.0 thing), so don't go hunting for reproducibility knobs. Same for negative prompts and CFG - this is a "point it and shoot" node, not a fine-control one.
Installing it
It's part of the official Runware pack:
cd ComfyUI/custom_nodes
git clone https://github.com/Runware/ComfyUI-Runware
pip install -r ComfyUI-Runware/requirements.txt
Restart, then add your key at ComfyUI Settings → Runware API key or via the RUNWARE_API_KEY environment variable. Dependencies are light - runware-sdk, pillow, soundfile - and there's nothing to download at install time.
Where people get burned
The trap is forgetting this is a paid API and treating it like your local SD install. It's cheap - the community's consensus is Runware's pricing is about the most transparent and bargain-basement around - but it's still metered, and a 20-result batch is still 20 charges. The other gotcha is expectations: 1.5 is a fast, economical model, not the flagship. When a prompt deserves the better engine, that's what the Pro tier and 2.0 are for. No API key set means instant errors, which is the pack's most common failure mode by far.
Inputs (17)
| 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. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |