Ideogram 2.0 Remix
Ideogram 2.0 Remix edits your image with a strength dial
- referenceImages
- advancedFeatures.watermark.image
- providerSettings.ideogram.styleReferenceImages
- image
Ideogram has been the benchmark for text-in-image since 2.0 launched in August 2024 and beat Flux Pro and DALL-E 3 in head-to-head tests - the KB notes it hit roughly 85-90% text rendering accuracy, which is why every graphic designer in the community quietly keeps an account even after open weights caught up. This node gives you the Remix variant through Runware's cloud, which means the "edit an existing image while keeping its text legible" use case, with one knob nobody else really has: a strength dial.
No local GPU, no checkpoint, no LoRA folder. The node calls Ideogram's API through the Runware SDK and hands you back a native IMAGE.
How it works
referenceImages is required - this is an edit, not a generation. The image goes up to Ideogram's remix pipeline along with your prompt, and providerSettings.ideogram.remixStrength (1-100, default 50) decides how much it changes. Crank it toward 100 and you get a dramatic reinterpretation; keep it low and you're doing guided touch-ups on the original composition. That's the whole point of Remix over the plain 2a model.
The inputs that matter
- referenceImages - the image to remix. Required.
- positivePrompt - what you want changed. "Make it autumn colors, keep the poster text" is the kind of prompt this model was built for.
- width / height - required, default 1024×1024. Output size.
- providerSettings.ideogram.remixStrength - the dial described above. This is the input you'll actually tweak.
- providerSettings.ideogram.styleReferenceImages - up to a few extra images for style guidance (works for the visual language, not the text).
- providerSettings.ideogram.colorPalette.name - a preset palette (EMBER, PASTEL, JUNGLE, …), or go custom via
advanced_jsonwithcolorPalette.members. - providerSettings.ideogram.magicPrompt -
AUTOrewrites your prompt for better adherence; flip toOFFif it's overriding your exact wording. - providerSettings.ideogram.styleType - AUTO, GENERAL, REALISTIC, DESIGN, RENDER_3D, ANIME, or FICTION. DESIGN is the one to remember for text-centric work.
- providerSettings.ideogram.renderingSpeed - TURBO is cheap and fast, QUALITY is the expensive render.
Plus the usual Runware fields: numberResults (up to 20), negativePrompt, seed, output format/quality, and the safety/TTL switches.
Installing
Install the pack once and every node in it appears together:
cd ComfyUI/custom_nodes
git clone https://github.com/Runware/ComfyUI-Runware
pip install -r ComfyUI-Runware/requirements.txt
Restart ComfyUI, or use ComfyUI Manager → search Runware. You need a Runware API key (Settings panel, RUNWARE_API_KEY, or runware auth login) and the dashboard's $20 minimum top-up.
Where people get burned
People set remixStrength at 100, lose the original entirely, and call it broken. It's not broken - that's what 100 means. Keep it 30-60 for edits that respect the source. And remember Ideogram's moderation is its own thing (it famously trains refusals in, per the KB's Ideogram 4 notes, and the API versions carry the same house style), so a refusal is the model's editorial opinion, not a node bug. negativePrompt is genuinely ignored unless guidance is active, so don't rely on it as your primary tool here.
Inputs (26)
| 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 | — | |
| negativePromptopt | STRING | Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1). | |
| 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.colorPalette.nameopt | COMBO | (default) | Preset color palette name. |
| 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. |
| advanced_jsonopt | STRING | Optional JSON merged into the request. For: providerSettings.ideogram.colorPalette.members |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |