Ideogram 2a Remix
The lightweight remix node that keeps your text
- referenceImages
- advancedFeatures.watermark.image
- providerSettings.ideogram.styleReferenceImages
- image
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.
Inputs (23)
| Name | Type | Default | Description |
|---|---|---|---|
| referenceImages | IMAGE | — | |
| positivePrompt | STRING | Text prompt describing elements to include in the generated output. | |
| advancedFeatures.watermark.imageopt | IMAGE | — | |
| providerSettings.ideogram.styleReferenceImagesopt | 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. | |
| providerSettings.ideogram.magicPromptopt | COMBO | AUTO | Automatic prompt enhancement. |
| providerSettings.ideogram.remixStrengthopt | INT | 501–100 | Transformation intensity for Remix models. Higher values create more dramatic changes. |
| providerSettings.ideogram.renderingSpeedopt | COMBO | DEFAULT | Generation speed/quality tradeoff. |
| safetyopt | BOOLEAN | false | Enable to set safety. Off uses the model's default. |
| safety.checkContentopt | BOOLEAN | false | Enable or disable content safety checking. |
| providerSettings.ideogram.styleTypeopt | COMBO | AUTO | Visual style and rendering approach. |
| 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 | — |