Exactly Bright Pulse
Reference-driven photos, zero prompt required
- referenceImages
- advancedFeatures.watermark.image
- image
Exactly Bright Pulse is a hosted, reference-driven photo model, and the first thing you'll notice is what's missing: there's no prompt box. The entire input contract is reference images plus a canvas size. You feed it pictures that establish the subject and the look, and the model carries that identity into a fresh generation. That's the whole trick, and for style-consistency work it's refreshing - no prompt-balancing act, no negative-prompt choreography, just "here's the vibe, make more like it."
The name is the aesthetic pitch: bright, high-key, luminous. If the look you want is punchy daylight and clean highlights, this is the variant in the Exactly photo family to reach for - the siblings split on contrast and warmth, and Bright Pulse sits firmly on the bright side.
What you set
referenceImages(required) - wired from the Runware Reference Images builder. That's where you actually work: each reference carries atype(its purpose), ataglike@actor1that links it to a mention, and the image itself. One or several; more refs means more consistent identity transfer.width/height- the output canvas, default 1024×1024.numberResults- up to 20 variations, each on its own seed. This is the iteration knob.watermark- optional builder output if you need one stamped in.outputFormat- JPG / PNG / WEBP, plusoutputQuality(20–99).
Output is image (IMAGE), ready for Preview Image or Save Image.
How it works
Mechanically it's the standard pack flow: build a request with the Exactly Bright Pulse model AIR and taskType: imageInference, send it over REST via the SDK, download the result as a native IMAGE. Your reference images are encoded and shipped with the request; the model runs in the cloud and the title bar reports the cost. The reason to use this over prompting a local checkpoint from scratch is consistency - the reference contract does the heavy lifting that tags and CFG wrestling would do locally.
Installing
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; deps are runware-sdk, pillow, soundfile. API key via Settings → Runware API key, RUNWARE_API_KEY, or runware auth login.
Troubleshooting
If results drift from your references, check the builder, not the model: references need a type and a tag, and a tag mismatch is the classic cause of identity loss. A missing or empty reference socket also means the job has nothing to hold onto - the socket is required for a reason. Want the same pipeline but punchier blacks? That's Exactly Extreme Contrast, the sibling that flips the tonal balance.
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| referenceImages | RUNWARE_REFERENCEIMAGES | — | |
| advancedFeatures.watermark.imageopt | IMAGE | — | |
| sizeopt | COMBO | 1K (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 | — |