---
title: Ideogram 4.5 Precise Edit | Runware Docs
url: https://runware.ai/docs/models/ideogram-4-5-precise-edit
description: Instruction-based image editing that restores every pixel the edit leaves untouched
---
# Ideogram 4.5 Precise Edit

![Ideogram 4.5 Precise Edit](https://assets.runware.ai/covers/ideogram-4-5-precise-edit.jpg)

Ideogram 4.5 Precise Edit is the precision editing variant of Ideogram 4.5. It applies a natural-language instruction to a source image, optionally limited by a mask and guided by up to four reference images, and restores unchanged pixels from the source so framing, color, and surrounding detail stay intact across many rounds of edits. It keeps the source dimensions and suits retouching, product and color changes, and multi-step design revisions.

- **Status**: live
- **ID**: `ideogram:4.5@precise-edit`
- Try in Playground
- **Creator**: Ideogram
- **Release Date**: September 30, 2026
- **Capabilities**: Image to Image, Edit, Checkpoint

## Pricing

$0.008 from, per run · ~33s per request

**Rates** (per run)

- Very low: `$0.008`
- Low: `$0.03`
- Medium: `$0.06`
- High: `$0.20`

**4 example generations**

- [image-to-image](https://runware.ai/docs/models/ideogram-4-5-precise-edit/examples#example-municipal-telephone-exchange-photo-restoration): `$0.20` (~28s)
- [reference-to-image](https://runware.ai/docs/models/ideogram-4-5-precise-edit/examples#example-heritage-railcar-interior-cleanup): `$0.20` (~40s)
- [inpaint](https://runware.ai/docs/models/ideogram-4-5-precise-edit/examples#example-offshore-survival-suit-night-relight): `$0.20` (~36s)
- [image-to-image](https://runware.ai/docs/models/ideogram-4-5-precise-edit/examples#example-historic-glasshouse-visitor-free-hero-image): `$0.20` (~30s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

When `inputs.maskImage` is provided, `inputs.referenceImages` is limited to 3 items.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-outputformat)

- **Type**: `string`
- **Default**: `JPG`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency).
- \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel).
- \`WEBP\`: Modern format providing superior compression and transparency support.

> [!NOTE]
> \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns complete results directly in the API response.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (1 property)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time.

### [ttl](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [seedImage](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-inputs-seedimage)

- **Path**: `inputs.seedImage`
- **Type**: `string`
- **Required**: true
- **File size**: `up to 25 MB`
- **Aspect ratio**: `1:6 to 6:1`

Image used as a starting point for the generation (UUID, URL, Data URI, or Base64). The output keeps its dimensions.

### [maskImage](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-inputs-maskimage)

- **Path**: `inputs.maskImage`
- **Type**: `string`
- **File size**: `up to 25 MB`

Image used to specify which areas of the input image should be edited (UUID, URL, Data URI, or Base64). White marks the area to edit, black is preserved. Must match the dimensions of `inputs.seedImage` and contain both white and black areas.

### [referenceImages](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `4`
- **File size (each)**: `up to 25 MB`
- **Aspect ratio (each)**: `1:6 to 6:1`

List of reference images (UUID, URL, Data URI, or Base64).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `ideogram:4.5@precise-edit`

Identifier of the model to use for generation.

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `10000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [seed](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [copyrightDetection](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-settings-copyrightdetection)

- **Path**: `settings.copyrightDetection`
- **Type**: `boolean`

Opt into post-generation copyright detection using Hive likeness and logo checks.

### [quality](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-settings-quality)

- **Path**: `settings.quality`
- **Type**: `string`
- **Default**: `high`

Rendering quality.

**Allowed values**: `very_low` `low` `medium` `high`

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-advancedfeatures-watermark)

- **Path**: `advancedFeatures.watermark`
- **Type**: `object (6 properties)`

Configuration object for adding watermarks to generated videos. Watermarks can be applied using either text or image content with customizable positioning and appearance. You must provide either `text` or `image` content for the watermark, but not both.

**Text watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "© 2025 Company",
    "displayPosition": "bottom-right",
    "opacity": 0.6,
    "fontColor": "#ffffff",
    "bgColor": "#000000"
  }
}
```

**Image watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "image": "c64351d5-4c59-42f7-95e1-eace013eddab",
    "displayPosition": "top-left",
    "opacity": 0.6
  }
}
```

**Tiled watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "PREVIEW",
    "tiled": true,
    "opacity": 0.4,
    "fontColor": "#cccccc"
  }
}
```

#### [text](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-advancedfeatures-watermark-text)

- **Path**: `advancedFeatures.watermark.text`
- **Type**: `string`
- **Min**: `2`
- **Max**: `32`

Watermark text.

#### [image](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-advancedfeatures-watermark-image)

- **Path**: `advancedFeatures.watermark.image`
- **Type**: `string`

Watermark image (UUID, URL, Data URI, or Base64).

#### [displayPosition](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-advancedfeatures-watermark-displayposition)

- **Path**: `advancedFeatures.watermark.displayPosition`
- **Type**: `string`

Watermark position.

**Allowed values**: `top-left` `top-center` `top-right` `center-left` `center-center` `center-right` `bottom-left` `bottom-center` `bottom-right` `tiled`

#### [opacity](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-advancedfeatures-watermark-opacity)

- **Path**: `advancedFeatures.watermark.opacity`
- **Type**: `float`
- **Min**: `0.1`
- **Max**: `1`
- **Step**: `0.01`

Watermark opacity.

#### [fontColor](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-advancedfeatures-watermark-fontcolor)

- **Path**: `advancedFeatures.watermark.fontColor`
- **Type**: `string`

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/ideogram-4-5-precise-edit#request-advancedfeatures-watermark-bgcolor)

- **Path**: `advancedFeatures.watermark.bgColor`
- **Type**: `string`

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/ideogram-4-5-precise-edit#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/ideogram-4-5-precise-edit#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [imageUUID](https://runware.ai/docs/models/ideogram-4-5-precise-edit#response-imageuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/ideogram-4-5-precise-edit#response-imageurl)

- **Type**: `string`
- **Format**: `uri`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/ideogram-4-5-precise-edit#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/ideogram-4-5-precise-edit#response-imagedatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output image.

### [seed](https://runware.ai/docs/models/ideogram-4-5-precise-edit#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/ideogram-4-5-precise-edit#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/ideogram-4-5-precise-edit#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### reference-to-image (reference-to-image)

![Heritage Railcar Interior Cleanup](https://assets.runware.ai/examples/ideogram-4-5-precise-edit/ccd6d78f-ff61-4c7d-bbb2-000bd7930038.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "cabf084b-3f0e-4d3c-8928-13c4a2c13efe",
  "model": "ideogram:4.5@precise-edit",
  "positivePrompt": "Create a meticulous, publication-ready cleanup of the seed photograph. Remove every visible piece of modern restoration equipment and temporary protection: the aluminum ladder, blue plastic sheeting, orange extension cables, work lights, tool cases, drop cloths, shop vacuum and any small loose tools. Generatively reconstruct only the interior surfaces and furnishings hidden behind those objects so the railcar appears fully restored, tidy and operational. Use reference image 1 as the architectural and appearance guide for the concealed banquettes, table positions, walnut panel divisions, brass trim, aisle boundaries, carpet pattern and period sconces. Use reference image 2 as the material and color guide for the satin walnut grain, softly aged brass, bottle-green mohair and burgundy-olive-cream woven carpet. Continue all lines, seams, reflections, shadows and repeating patterns naturally through the cleared areas with correct perspective and scale. Match the seed image's overcast window light, warm interior exposure, camera position, lens character and documentary realism. Preserve the original framing and all unaffected pixels, including the windows, exterior view, ceiling, visible historic fittings and unobstructed upholstery. Do not redesign the railcar, add people, add signage, add decorative objects or introduce contemporary furniture. The result should look like a single authentic heritage documentation photograph captured after restoration, with no evidence that equipment was ever present.",
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/d7dabc07-df84-4ee6-9c18-34280f23f78d.jpg",
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/2b0e96a9-03fe-41f2-9253-2d45ff220ee8.jpg",
      "https://assets.runware.ai/assets/inputs/a8ad5dd1-3fe6-48a1-b263-90ae82de1952.jpg"
    ]
  }
}
```

---

### image-to-image (image-to-image)

![Municipal Telephone Exchange Photo Restoration](https://assets.runware.ai/examples/ideogram-4-5-precise-edit/b8fb3b69-5b06-4e34-be07-e4e8a68f99af.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "7e43397c-521c-4f8c-b0c5-e6a9fb9dbfca",
  "model": "ideogram:4.5@precise-edit",
  "positivePrompt": "Restore and colorize this damaged 1949 municipal telephone exchange photograph as an exhibition-quality archival image. Remove the fold crease, scratches, dust, water stains, edge discoloration and cracked or missing emulsion, reconstructing only the image information required by those damaged areas. Correct fading and uneven exposure while retaining natural period photographic grain and gentle mid-century lens softness. Apply restrained, historically plausible color throughout: muted sage-green painted metal switchboards, dark brown and black patch cords, small amber and red indicator lamps, warm oak furniture, cream plaster walls, subdued navy, burgundy, tan and pale blue clothing, natural skin tones and softly cool daylight from the windows. Preserve the exact composition, crop, perspective, people, facial identities, expressions, poses, hairstyles, headsets, clothing construction, equipment layout, desk objects, lighting direction and room architecture. Keep every operator recognizable and do not beautify, modernize or restage the scene. Do not add or remove people, controls, furniture, signs or objects. The finished result should look like a carefully conserved and professionally hand-colorized original photograph, not a newly staged digital photograph.",
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/15068d41-5574-48ca-853e-0cab53d9cef3.jpg"
  }
}
```

---

### image-to-image (image-to-image)

![Historic Glasshouse Visitor-Free Hero Image](https://assets.runware.ai/examples/ideogram-4-5-precise-edit/07c08aa9-8664-46bb-b7f0-6dd756797392.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "797799d5-a76f-45a5-b7de-10e296e6689e",
  "model": "ideogram:4.5@precise-edit",
  "positivePrompt": "Create a polished visitor-free heritage tourism photograph from this exact source image. Remove every person and all temporary visitor or maintenance objects throughout the scene, including the tour group, isolated visitors, velvet rope stanchions, freestanding information boards, yellow hose, cleaning cart, and litter bins. Naturally reconstruct the concealed sections of the patterned tile walkway, planting beds, foliage, railings, and distant architecture with correct perspective, texture, shadows, and reflections. Keep the original camera position, wide-angle framing, symmetrical composition, Victorian white iron framework, glass roof, mature tropical plants, warm late-afternoon sunlight, humid haze, color palette, and photographic realism unchanged. Preserve permanent architectural and botanical details precisely. The finished image should look like an authentic photograph captured moments before opening, immaculate but not sterile, with no people, barriers, signs, equipment, duplicated foliage, retouching artifacts, or unexplained empty patches.",
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/a57cfd72-d5ce-407a-8415-1f4c79d35378.jpg"
  }
}
```

---

### inpaint (inpaint)

![Offshore Survival Suit Night Relight](https://assets.runware.ai/examples/ideogram-4-5-precise-edit/1d7c90bd-b833-45fb-9ce5-ec6cf9685543.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "7910114b-a6ba-43cc-851d-ccb77fdb8391",
  "model": "ideogram:4.5@precise-edit",
  "positivePrompt": "Transform the entire rescue technician in the seed image from flat studio illumination into a convincing nighttime ship-searchlight demonstration, using the reference image for the direction, contrast, color temperature and realistic response of the retroreflective material. Preserve the technician’s exact identity, stance, anatomy, silhouette, camera angle, scale and position, and retain every specific construction detail of the original immersion suit, including its hood, zipper, seams, reinforced knees, gloves, boots and reflective-panel placement. Apply a powerful cool-white key light from high camera-left across the whole figure. Create crisp directional modeling, controlled deep shadows on the camera-right side and a restrained cool rim highlight along the shadow edge. Make the silver reflective panels return brilliant clean white light like genuine marine-grade retroreflective tape, visibly brighter than the surrounding fabric but still retaining their edges, shape and surface texture. Keep the fluorescent red-orange fabric saturated yet naturally darker under night conditions, with realistic folds, waterproof texture and specular response. Do not alter any unmasked part of the image: preserve the original seamless dark-navy background, framing and empty space exactly. The finished result must read as a premium, technically credible maritime safety-equipment catalog photograph, not a composite or illustration. No added props, scenery, fog, lettering, branding or logos.",
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/b9585e90-fce7-468e-b92b-7c2902273920.jpg",
    "maskImage": "https://assets.runware.ai/assets/inputs/9f8ad7a7-0769-4270-9547-33560febbce9.png",
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/44854c9d-1ee0-421c-a759-a22090feb703.jpg"
    ]
  }
}
```