ComfyUI Node

Exactly Distant Reality

Reference in, out-of-focus world out

By Runware·Created 2 years ago·Updated about a month ago· 140
Exactly Distant Reality
  • referenceImages
  • advancedFeatures.watermark.image
  • image
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

Distant Reality is the Exactly photo variant with its eye on atmosphere. The name points at the mood - a subject held at a remove, background falling into soft focus, space doing the storytelling. It's the node for the shot that's about context and depth rather than a face filling the frame, and it gets there the same way every Exactly photo node does: from reference images, with no prompt field in sight.

If you're doing environmental portraiture, establishing shots, or anything where the subject sits inside a world instead of on top of it, this is the variant to try first. The other Exactly nodes split on brightness and contrast; Distant Reality is the one that reaches for depth. You feed it references that define who and what the look is, and it renders at the canvas you ask for.

What you set

  • referenceImages (required) - wired from the Runware Reference Images builder: each ref takes a type, a tag (like @subject) linking it to a mention, and the image itself. Stack several for a stronger identity hold.
  • width / height - output canvas, default 1024×1024. Wide aspect ratios suit this model's mood.
  • numberResults - up to 20 seeded variations per run.
  • watermark - optional, from the watermark builder.
  • outputFormat - JPG / PNG / WEBP, with outputQuality 20–99.

Output is image (IMAGE).

How it works

Standard pack plumbing: the node sends a taskType: imageInference request with the Exactly Distant Reality model AIR over REST through the Runware SDK, encoding your reference images into the payload, and downloads the result as a native IMAGE. It's a cloud generation - no checkpoint to download, no local VRAM, cost printed on the title bar. The reference contract is doing the consistency work that local workflows would handle with a dozen prompt-tuning nodes.

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

Identity drift again points at the reference builder - verify type and tag are set on every ref. If the "distant" look reads as mushy instead of atmospheric, try more references of the actual subject rather than of the scene; the model holds onto people better when it has them from several angles. And for a warmer, closer-feeling take on the same pipeline, Exactly Warm Light is the sibling to switch to.

CategoryRunware/Image/exactly

Inputs (17)

NameTypeDefaultDescription
referenceImagesRUNWARE_REFERENCEIMAGES
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.

Outputs (1)

NameTypeDescription
imageIMAGE