ComfyUI Node

Ideogram 2a Remix

The lightweight remix node that keeps your text

By Runware·Created 2 years ago·Updated about a month ago· 140
Ideogram 2a Remix
  • referenceImages
  • advancedFeatures.watermark.image
  • providerSettings.ideogram.styleReferenceImages
  • 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
providerSettings.ideogram.magicPromptAUTO
providerSettings.ideogram.remixStrength50
providerSettings.ideogram.renderingSpeedDEFAULT
safetyfalse
safety.checkContentfalse
providerSettings.ideogram.styleTypeAUTO
ttlfalse
ttl_value60
outputFormatJPG
outputQuality95

Ideogram 2a Remix is the small sibling of 2.0 Remix - same idea, same required inputs, a slightly slimmer set of options. You feed it an image, tell it what to change, and it comes back with a remixed version that - because it's Ideogram - usually keeps any text in the original legible. If you've ever tried to edit an image with a local model and watched the storefront sign turn into gibberish, you know exactly why this is worth having.

Like every node in the Runware/ComfyUI-Runware pack, it's an API call: no model files, no local GPU, native IMAGE out.

How it works

referenceImages is required and providerSettings.ideogram.remixStrength (1-100, default 50) is the heart of it. Low values respect the source and make surgical tweaks; high values reinterpret the whole scene. The 2a Remix variant differs from 2.0 Remix mostly by trimming options - there's no color-palette preset dropdown here, and styleType stops at the five core choices (AUTO, GENERAL, REALISTIC, DESIGN, ANIME) instead of the seven the 2.0 node carries.

The inputs that matter

  • referenceImages - required. The image being remixed.
  • positivePrompt - the change you want.
  • width / height - required, 1024 default.
  • providerSettings.ideogram.remixStrength - the dial. Start at 30-60; reserve the top of the range for deliberate full reworks.
  • providerSettings.ideogram.styleReferenceImages - optional style guidance alongside the content reference.
  • providerSettings.ideogram.magicPrompt - AUTO vs OFF; flip off when your wording is exact.
  • providerSettings.ideogram.renderingSpeed - TURBO / DEFAULT / QUALITY, the cost-quality tradeoff.
  • providerSettings.ideogram.styleType - pick DESIGN for text-heavy work.

Plus the usual numberResults (up to 20), seed, watermark, output format/quality, safety, and TTL fields.

Installing

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

Restart, or install through ComfyUI Manager by searching Runware. API key via Settings, RUNWARE_API_KEY, or runware auth login.

Common issues

The two traps are the same as 2.0 Remix: setting remixStrength to 100 and being shocked the image changed completely, and blaming the node when Ideogram's own content filter declines a prompt. One genuine difference to know: this is the 2a-class model, so expect slightly less raw quality than the 2.0 Remix node on complex compositions - it's the cheaper engine, not a downgrade trap. If the 2.0 node's results are worth the extra cents to you, use it; if you're batching a lot of quick variations, this one keeps the bill down.

CategoryRunware/Image/ideogram

Inputs (23)

NameTypeDefaultDescription
referenceImagesIMAGE
positivePromptSTRINGText prompt describing elements to include in the generated output.
advancedFeatures.watermark.imageoptIMAGE
providerSettings.ideogram.styleReferenceImagesoptIMAGE
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.
providerSettings.ideogram.magicPromptoptCOMBOAUTOAutomatic prompt enhancement.
providerSettings.ideogram.remixStrengthoptINT501–100Transformation intensity for Remix models. Higher values create more dramatic changes.
providerSettings.ideogram.renderingSpeedoptCOMBODEFAULTGeneration speed/quality tradeoff.
safetyoptBOOLEANfalseEnable to set safety. Off uses the model's default.
safety.checkContentoptBOOLEANfalseEnable or disable content safety checking.
providerSettings.ideogram.styleTypeoptCOMBOAUTOVisual style and rendering approach.
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