Wireflow is now a Claude connector.

Set it up→

Ideogram 4.5 Edit

Copy agent promptDownload schemaOpen in a workflowCopy link

Ideogram 4.5 editing. precise multi-turn edits with no artifact buildup, and text edited in place or translated.

Image to imageFrom 19 creditsIdeogram

Input

9 fields

Result Idle

Your result will appear here.

Set your inputs, then open a workflow to create it.

Credit estimate uses the model defaults. Your workflow shows the final estimate for your inputs before you run.

Pairs well with

ByteDance

Seedance 2.5

ByteDance Seedance 2.5. Generates video from a prompt alone, or from reference material: up to 8 reference images and videos in any mix (5 on the older inline route), plus up to 2 reference audio tracks.

Video~135 credits at default settings
Google

Gemini Omni Flash 1.1

Google Gemini Omni Flash 1.1. generate video with audio from text, an image, reference images or videos, or an existing video.

Video~128 credits at default settings
Model guide

Build with Ideogram 4.5 Edit.

Ideogram 4.5 editing. precise multi-turn edits with no artifact buildup, and text edited in place or translated.

Read the Ideogram 4.5 Edit docs

Best for

Ideogram 4.5 editing. precise multi-turn edits with no artifact buildup, and text edited in place or translated. Use the playground to set up a single step, then open a workflow when you want to connect more tools.

Inputs explained

Prompt (required)
Set the prompt used by this model. Type: text.
Image (required)
The image to edit. Type: image.
Mask (optional)
Optional. Same size as the image; black is edited, white is kept. Type: image.
Reference Images (optional)
Up to 4 references (3 when a mask is wired). Type: list of image.
Edit Precision (optional)
High uses Precise Edit and restores every pixel you did not ask to change. Type: text. Options: Regular, High (Precise Edit). Default: "regular".
Quality (optional)
Set the quality used by this model. Type: text. Options: , , , . Default: "medium".
Image Size (optional)
Only Regular edits without a mask can change size; otherwise the source size is kept. Type: text. Options: Match source, Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9. Default: "auto".
Number of Images (optional)
Set the number of images used by this model. Type: number. Minimum: 1. Maximum: 8. Default: 1.
Seed (optional)
Set the seed used by this model. Type: number.

Tips before you run

Start with the default settings and change one input at a time. Keep the result you like on your board so the next step can use it.

If you add a reference file, use a link the workflow can read. Check the inputs and credit estimate on the board before starting a run.

Working with this model

What it is best at

Edits you stack. Run the output back into this node as many times as you like: Ideogram 4.5 does not build up artifacts turn after turn, so the tenth edit looks as clean as the first. It also edits text in place (fix a typo on a poster, swap a price, translate a sign) while keeping the font and layout.

Regular or High precision

Regular regenerates the whole image around your instruction and is the only mode that can change the output size. High uses Precise Edit and restores every pixel you did not ask to change, which is what you want for text fixes and small product tweaks.

Pricing

Per image, whatever the size. Four tiers, Very Low, Low, Medium and High, and a higher tier costs more.

Common questions

How do I use Ideogram 4.5 Edit on Wireflow?

Set the inputs above and choose Open in a workflow. Sign in to save your board, then check its credit estimate before you run.

Can I use Ideogram 4.5 Edit through an API?

Yes. Save a workflow with this model, then call the Wireflow run API with its workflow ID. The API tab has examples you can copy.

What changes the credit price?

The price shown uses the model defaults. Your inputs and model settings can change the total. The workflow shows an estimate before you run.

Can I connect this to another model?

Yes. Open it in a workflow and connect its output to another node with a matching input type.