26.1 Overview

Image Generator is AIUNIFY PROS SUITE’s specialized AI Marketing workspace for creating visual marketing assets from written prompts and optional reusable Product and Avatar references.

The workspace itself is titled:

Text-to-Image Generator

with the description:

“Create stunning marketing visuals with AI.”

The current Image Generator supports subscriber-facing workflows for:

  1. Writing an image-generation Prompt
  2. Selecting a reusable Product Reference
  3. Uploading Product Reference images
  4. Selecting a reusable AI Avatar
  5. Combining Product and Avatar references
  6. Choosing a Square, Landscape, or Portrait output ratio
  7. Starting asynchronous AI image generation
  8. Monitoring the generation state
  9. Handling provider/safety errors
  10. Previewing the completed Image
  11. Regenerating another Image
  12. Downloading the current result
  13. Reviewing persistent Generation History
  14. Opening saved Images in Asset Viewer
  15. Zooming generated Images
  16. Downloading historical Images
  17. Copying historical Image URLs

26.2 Where Image Generator Is Located

Navigate to:

Sidebar → AI Marketing → Image Generator

The current route is:

/ai-marketing/image-generator

The Tool also appears on the Marketing Studio Dashboard under:

Text-to-Image.

26.3 Image Generator vs. Text-to-Image

The system currently uses two related Names.

Sidebar

Image Generator

Marketing Studio / Workspace

Text-to-Image

and:

Text-to-Image Generator

They refer to the same current workspace.

26.4 Authentication Is Required

Image Generator checks whether the subscriber is authenticated.

If the session is unavailable, the page redirects toward:

/login.

26.5 Current Route-Level Access Behavior

The Image Generator page performs its own authentication check.

The supplied source does not show a separate page-level FeatureGuard wrapper around this specialized generator.

Normal Sidebar, Plan, or system configuration can still affect whether the Tool is available to the subscriber.

26.6 Image Generator Is Not the Standard AI Generator

This Tool does not use the Standard AI Generator workspace from Chapter 12.

It uses a specialized Marketing media-generation service with:

  1. Asynchronous Task creation
  2. Task ID
  3. Status polling
  4. Media Asset storage
  5. Marketing Asset History

26.7 Main Workspace Layout

The current Image Generator contains two primary columns.

Left

Generation controls

Right

Image Preview/result area

Below them is:

Generation History.

26.8 Left-Side Controls

The current creation controls include:

  1. Prompt
  2. Product Reference
  3. AI Avatar
  4. Resolution
  5. Style
  6. Generate Masterpiece

26.9 Prompt Label

The image Prompt section is labeled:

Imagine...

26.10 Prompt Placeholder

The current example is:

“E.g. A futuristic luxury watch displayed on a marble pedestal with dramatic lighting...”

26.11 Prompt Is Required

Image Generator will not intentionally start a generation with an empty Prompt.

If you attempt to generate without one, the exact current message is:

Please enter a prompt.

26.12 No Current Prompt Character Counter

The Textarea does not establish:

  1. Visible character count
  2. maxLength
  3. Subscriber-facing Prompt length limit

Keep Prompts focused and descriptive.

26.13 Prompt Is Disabled During Generation

Once generation is active, the Prompt Textarea is disabled until the operation finishes or fails.

This prevents the visible Prompt from being edited while the current task is processing.

26.14 Build the Prompt Around the Desired Final Image

Useful Prompt elements include:

  1. Main subject
  2. Environment
  3. Camera angle
  4. Composition
  5. Lighting
  6. Mood
  7. Color palette
  8. Audience
  9. Marketing purpose
  10. Product placement
  11. Clothing
  12. Background
  13. Level of realism

26.15 Weak Prompt

For example:

“Business software ad.”

leaves most creative decisions to the generator.

26.16 Stronger Prompt

For example:

“Premium enterprise software advertisement showing a diverse sales leadership team reviewing an AI-powered business dashboard in a modern executive office, dramatic cinematic lighting, sophisticated black and burgundy accents, polished commercial photography, clean negative space for headline placement.”

This gives the generator much stronger visual direction.

26.17 Describe the Subject Clearly

If a particular subject matters, identify:

  1. Who or what should appear
  2. Where it should appear
  3. What it should be doing
  4. Which visual elements should receive emphasis

26.18 Describe Composition

Useful directions can include:

  1. Centered Product
  2. Wide cinematic composition
  3. Subject on the right
  4. Negative space on the left
  5. Close-up
  6. Overhead view
  7. Full-body portrait
  8. Product hero shot

26.19 Describe Lighting

Examples:

  1. Soft studio lighting
  2. Dramatic rim lighting
  3. Golden-hour lighting
  4. High-key commercial lighting
  5. Moody cinematic lighting
  6. Neon ambient lighting

26.20 Describe Brand Colors Explicitly

If brand consistency matters, state the desired palette directly.

For example:

“Use burgundy, black, white, and subtle gold accents. Avoid bright blue as the dominant color.”

26.21 Specify Marketing Use

You can also explain the intended purpose.

For example:

  1. Social media advertisement
  2. Website hero
  3. Product launch
  4. LinkedIn campaign
  5. Event promotion
  6. Sales brochure background
  7. Email marketing creative

This can help the generated composition match the intended business use.

26.22 Avoid Relying on AI for Critical Written Text

If the generated image contains important:

  1. Product Names
  2. Prices
  3. URLs
  4. Phone numbers
  5. Legal text
  6. Headlines

inspect them carefully.

AI-generated visual text can contain spelling or character errors.

26.23 Product Reference

Below the Prompt, Image Generator includes:

Select Product Reference.

This allows a previously uploaded Product image to guide generation.

26.24 Product Reference Is Optional

You can generate an Image using only the written Prompt.

A Product Reference is not required.

26.25 Upload Product

If the Product you need is not already available, select:

Upload Product.

26.26 Product Upload Accepts Images

The Product Picker accepts:

image/*

and explicitly checks that the selected file's MIME type begins with:

image/.

26.27 Non-Image Product Upload

If the file is not recognized as an Image, the exact current notification is:

Please upload an image file.

26.28 No Product Image Size Limit Is Established Client-Side

The current shared Product Picker source does not contain a subscriber-side file-size validation check.

Therefore, this manual does not invent a Product Reference size limit.

A server/service may still impose limits that are outside this sanitized client source.

26.29 Product Image Is Converted for Upload

The Product Picker reads the selected Image as browser Base64 data before sending it into the Marketing upload workflow.

26.30 Product Name Comes from the Filename

When uploaded, the Product Name is derived from the file Name without the extension.

For example:

AIUNIFY_CRM_Dashboard.png

produces a Product reference Name based on:

AIUNIFY_CRM_Dashboard

26.31 Best Practice — Rename Product Files Before Uploading

Instead of:

IMG_4289.png

use:

AIUNIFY_Pro_Suite_Interface.png

This makes the reusable Product reference easier to recognize later.

26.32 Product Uploaded Successfully

When the upload succeeds, the current message is:

Product uploaded successfully.

The Product list is then refreshed.

26.33 Product Upload Failure

Possible current messages include:

Upload failed

or the specific returned Error.

26.34 Product Upload Exception

If the request itself encounters an Error, the current message is:

An error occurred during upload.

26.35 No Products Uploaded Yet

If the reusable Product collection is empty, the Picker displays:

No products uploaded yet.

26.36 Selecting a Product Reference

Choose a Product thumbnail.

The selected Product receives:

  1. Highlighted styling
  2. Check indicator


26.37 Product Reference Persists as a Reusable Marketing Input

Product Picker retrieves existing references from:

list-products.

This means uploaded Products are intended to be reusable across supported AI Marketing generators.

26.38 Product Reference Alters the Generation Prompt

When a Product is selected, Image Generator:

  1. Adds the Product image URL to the generation reference list.
  2. Appends the instruction:

“Feature the product shown in the provided reference photo prominently.”


26.39 Product Reference Is More Than a Thumbnail

The selected Product URL is actually sent with the generation request.

It therefore acts as an AI reference input rather than simply an interface label.

26.40 Product Reference Is Not a Pixel-Perfect Guarantee

The generator is instructed to feature the Product reference.

The source does not establish deterministic pixel-perfect Product reproduction.

Inspect:

  1. Logo
  2. Shape
  3. Color
  4. Packaging
  5. Labels
  6. Product proportions

before publication.

26.41 No Direct Remove/Deselect Control Is Visible in Product Picker

The current Product Picker exposes selectable Product thumbnails but does not render a dedicated:

Clear Product

button in the component.

If you need a clean no-reference generation, the current UI may require reloading/re-entering the workspace if simply selecting another Product does not meet your need.

26.42 AI Avatar Reference

Image Generator also includes:

Select AI Avatar.

26.43 Avatar Reference Is Optional

You can generate with:

  1. No Avatar
  2. Avatar only
  3. Product only
  4. Product + Avatar

26.44 Existing Avatars Are Reusable

The Avatar Picker retrieves the current Avatar collection from:

list-avatars.

26.45 No Avatars Found

If no reusable Avatar exists, the exact message is:

“No avatars found. Create one in the Avatar Studio.”

26.46 New Avatar

Select:

New Avatar

to open:

/ai-marketing/avatar-studio.

The detailed Avatar-generation workflow is covered in Chapter 28.

26.47 Selecting an Avatar

Choose an Avatar thumbnail.

The selected Avatar receives visual highlighting and a Check indicator.

26.48 Avatar Reference Alters the Prompt

If an Avatar is selected, Image Generator adds the Avatar image to the reference list and appends:

“Include the person shown in the provided reference photo as the main character.”

26.49 Product + Avatar

If both are selected, another instruction is appended:

“The person should be naturally interacting with or showcasing the product.”

26.50 Product + Avatar Workflow

A useful marketing workflow is:

Select Product


Select AI Avatar


Prompt:

“Create a premium enterprise campaign image showing the spokesperson demonstrating the Product in a modern business environment.”

Generate

This tells the service to combine both reusable references.

26.51 Reference Consistency Still Requires Review

When combining references, inspect carefully for:

  1. Face consistency
  2. Clothing/body artifacts
  3. Product distortion
  4. Hand placement
  5. Product logos
  6. Relative scale

26.52 No Generic Local Reference-Image Upload Field

The Image Generator itself does not expose a general control labeled:

  1. Upload Reference Image
  2. Image-to-Image
  3. Edit Existing Image

Its current reusable reference inputs are specifically:

  1. Product Reference
  2. AI Avatar

26.53 Product Upload Can Serve as the Current Product-Image Input Path

If you need a new Product reference:

Upload Product → Select it → Generate

The generator then uses that stored Product Image in the request.

26.54 No Direct Inpainting Workflow

The current Image Generator does not establish:

  1. Paint mask
  2. Replace selected region
  3. Generative fill
  4. Inpainting
  5. Outpainting

26.55 No Background Removal Control

There is no source-verified:

Remove Background

function in this Image Generator workspace.

26.56 Resolution

The current control is labeled:

Resolution.

However, its available values are aspect/size ratios rather than pixel dimensions.

26.57 Available Resolution Choices

The visible options are:

  1. Square (1:1)
  2. Landscape (3:2)
  3. Portrait (2:3)


26.58 Default Size

The current default is:

1:1.

26.59 Square

Use:

Square (1:1)

for compositions such as:

  1. Social post
  2. Product card
  3. Profile-style marketing visual
  4. General square creative

26.60 Landscape

Use:

Landscape (3:2)

when you want a wider composition.

Examples:

  1. Website visual
  2. Wide advertisement
  3. Editorial/banner-style creative

26.61 Portrait

Use:

Portrait (2:3)

when you want a taller image.

Examples:

  1. Poster
  2. Portrait advertisement
  3. Vertical creative

26.62 “Resolution” Does Not Specify Pixel Count

The selector does not expose values such as:

  1. 1024 × 1024
  2. 1920 × 1080
  3. 4K

The selected value is sent to the Marketing service as:

options.size.

Therefore:

Do not interpret the current Resolution selector as a precise pixel-resolution control.

26.63 No 16:9 Option

The current Text-to-Image Generator does not offer:

16:9

in this selector.

The verified choices are only:

  1. 1:1
  2. 3:2
  3. 2:3

26.64 No 9:16 Option

Likewise, there is no current:

9:16

Image Generator selection.

26.65 Style

The interface includes a second selector labeled:

Style.

26.66 Visible Style Choices

The current options are:

  1. Photorealistic
  2. Digital Art
  3. Cinematic
  4. 3D Render


26.67 Default Style

The current component initializes Style as:

realistic

which corresponds to:

Photorealistic.

26.68 Important Current-Version Limitation — Style Is Not Sent

Although the Style selector is visible and its state changes when you choose a Style, the current handleGenerate request does not include the style state.

The request sends:

  1. Prompt
  2. Size
  3. Enhancement flag
  4. Reference URLs

but not the selected Style.

26.69 Style Is Therefore Not Source-Verified to Affect the Current Output

This is an important implementation distinction.

You can visibly choose:

  1. Photorealistic
  2. Digital Art
  3. Cinematic
  4. 3D Render

but the current client does not transmit that choice to /api/marketing.

Therefore:

The Style selector is currently visible UI, but its effect on generation is not source-verified.

26.70 Put Critical Style Direction in the Prompt

Until the Style selection is confirmed to be wired into generation, write important visual-style instructions directly in the Prompt.

For example:

“Photorealistic commercial photography with natural skin texture and realistic lighting.”

or:

“Premium 3D render with realistic materials, ray-traced studio lighting, and high-end product visualization.”

26.71 Do Not Depend on the Style Dropdown Alone

If a particular aesthetic matters:

Select the desired Style

and also:

State the Style in the Prompt.

This is the safest current user workflow.

26.72 Generate Masterpiece

The primary action button is:

Generate Masterpiece.

26.73 Starting Generation

Select:

Generate Masterpiece

after completing the Prompt and any desired reference/settings choices.

26.74 Generating...

Once active, the button changes to:

Generating...

26.75 Generate Button Is Disabled During Processing

You cannot start another generation with that same main button while the current generating state is active.

26.76 Current Request Structure

The Image Generator sends:

  1. action: generate-image
  2. Final Prompt
  3. Selected size
  4. isEnhance: true
  5. Reference image URLs

to the specialized Marketing API.

26.77 Image Enhancement Is Always Requested

The current client sends:

isEnhance: true

for Image generation.

There is no user-facing toggle to disable that enhancement behavior.

26.78 No Enhancement Strength Control

The current UI does not provide:

  1. Enhance amount
  2. Prompt enhancement toggle
  3. Enhancement strength

26.79 Specialized Marketing Service

Image Generator does not submit the request through the normal /api/ai/stream text-generation workflow.

It posts to:

/api/marketing

with:

action: generate-image.

26.80 Header Language Model Is Not Used by This Client

The Image Generator component does not retrieve or submit:

  1. selectedModel
  2. Manual Model state

in its generation request.

Therefore:

Changing the normal PROS SUITE Header AI Model is not source-verified to change Text-to-Image generation.

26.81 No Image-Generation Model Selector

The current Image Generator does not expose a user-facing choice such as:

  1. Image Model A
  2. Image Model B
  3. Provider selector

26.82 No User API-Key Headers Are Sent by the Client

The Image Generator request sends ordinary JSON headers to /api/marketing.

It does not append the subscriber's provider API-Key headers used by the shared text-generation workflows.

Therefore, Chapter 11's BYOK AI Model configuration is not source-verified as controlling this Image-generation operation.

26.83 Kie.ai Is Identified in the Current Processing Interface

While an Image is processing, the current interface states:

“Kie.ai is processing your high-resolution marketing image.”

This indicates the current specialized media-generation workflow is integrated with Kie.ai at the user-interface level.

26.84 Generation Is Asynchronous

The initial generation request does not immediately return the final Image.

Instead, a successful start returns a:

taskId

which the client stores for later status checks.

26.85 Generation Started

When the initial task begins successfully, the current notification is:

Generation started. Please wait...

26.86 Polling

While a Task ID exists and generation remains active, Image Generator checks the status approximately every:

5 seconds.

26.87 Polling Continues Until Success or Failure

The current client keeps polling until the provider/service reports:

  1. success
  2. failed

or the component is otherwise removed.

26.88 No Subscriber-Facing Poll Button

Status checking happens automatically.

You do not need to select:

Check Status

manually.

26.89 No Stop Generation Control

Unlike Game Developer, Image Generator does not currently expose:

Stop Generation

or:

Cancel Generation.

Once a task starts, the client waits for a success/failure state.

26.90 No Client-Side Timeout Is Established

The polling logic does not define a fixed user-facing timeout such as:

  1. 60 seconds
  2. 5 minutes

before automatically canceling the task.

26.91 Creating Your Vision...

During generation, the Preview displays:

Creating your vision...

26.92 Processing Message

Below that is:

“Kie.ai is processing your high-resolution marketing image.”

26.93 Animated Progress Bar

The current generating screen includes a horizontal Progress animation.

Its animation is configured to fill from 0% to 100% over:

30 seconds.

26.94 The 30-Second Progress Bar Is Not Actual Task Progress

The animation is simply configured with a 30-second visual duration.

It is not linked to:

  1. Provider progress percentage
  2. Number of generation stages
  3. Task completion percentage

Therefore:

Do not interpret the animated bar as an exact generation-progress measurement.

26.95 Generation Can Continue After the Bar Fills

Because task completion is controlled by 5-second status polling, the actual Image can still be processing even if the visual progress animation has reached the end.

Wait for the success notification/result.

26.96 Current Result Is Cleared Before a New Generation

When generation begins, Image Generator sets the previous current result to empty before starting the new task.

Therefore, preserve an important Image through:

  1. Download
  2. Generation History

before intentionally starting another generation if needed.

26.97 Successful Generation

When polling reports success, the current client:

  1. Takes the first URL from the returned result list.
  2. Sets it as the current result.
  3. Stops the generating state.
  4. Clears Task ID.
  5. Displays success.
  6. Refreshes Generation History.


26.98 Image Generated Successfully!

The exact success notification is:

Image generated successfully!

26.99 First Returned Image Is Used for the Current Result

The current client explicitly uses:

status.resultUrls[0].

Therefore, the current result area is designed around one returned Image.

26.100 No Number-of-Images Selector

The Image Generator does not expose a control for:

  1. 1 Image
  2. 2 Images
  3. 4 Images
  4. Batch quantity

The current result workflow uses one primary returned URL.

26.101 No Seed Control

There is no source-verified subscriber setting for:

Seed.

26.102 No Negative Prompt

The current interface does not include a separate:

Negative Prompt

field.

Put avoidance instructions into the main Prompt where appropriate.

Example:

“No text, no watermark, no blue background.”

26.103 No Guidance Scale

There is no user-facing:

  1. CFG
  2. Guidance Scale
  3. Prompt strength

control.

26.104 No Sampling Steps

The Image Generator does not expose a:

Steps

control.

26.105 No Batch Variations Control

There is no source-verified:

Generate 4 Variations

button.

Regeneration starts another full generation request.

26.106 Content-Policy Failure Detection

If task polling returns an Error containing wording related to:

  1. Content policy
  2. Flagged

the Image Generator treats it as a safety-filter condition.

26.107 Current Safety-Filter Message

The current message is:

“Your prompt was flagged by the AI safety filter. Try rephrasing — avoid mentioning real people, brands, or sensitive topics.”

26.108 Safety Filter Is Provider/System Behavior

A safety rejection means the generation service declined the Prompt.

Revise the Prompt rather than repeatedly submitting identical text.

26.109 Be Careful With Real-Person Instructions

The current Error guidance specifically mentions avoiding:

real people

when a Prompt is flagged.

If a request involving a named public/person subject fails, rework the creative direction appropriately.

26.110 Brand References Can Also Trigger the Current Filter Guidance

The current safety message also mentions:

brands.

If a brand-heavy Prompt is rejected, try describing the desired Product or visual characteristics in a more general way when appropriate.

26.111 Sensitive Topics

The same message references:

sensitive topics.

Keep marketing-generation Prompts appropriate for the service.

26.112 Credits Insufficient

The polling logic also detects the phrase:

credits insufficient.

This is distinct from the PROS SUITE Monthly Tokens display.

26.113 Provider Credits vs. PROS SUITE Tokens

The current client exposes the possibility of a media-provider credit Error while the general Feature catalogue separately lists a PROS SUITE Token reference for Marketing Image generation.

These are not automatically the same accounting system.

26.114 Demo-Specific Credits Message

In a specific demo-domain condition, insufficient provider credits cause:

“In the demo, this feature is disabled”.

This is demo-specific source logic and should not be interpreted as a standard production subscriber message.

26.115 General Generation Failure

If task polling reports a normal failure, Image Generator displays the returned Error or:

“Generation failed. Please try a different prompt.”

26.116 Failed Initial Request

If the Marketing service refuses to start the generation, the current UI displays the returned Error or a message based on:

Failed to start generation.

26.117 Unexpected Server Response

If the initial response cannot be parsed as expected, the client creates an Error in this pattern:

Unexpected response from server ([status]).

26.118 Request-Level Failure

If the request itself throws an Error, the fallback is:

Image generation request failed.

26.119 Current Result Preview

After successful generation, the completed Image appears in the large right-side result area.

26.120 Image Fit

The current result uses:

object-contain

so the complete Image is intended to fit inside the Preview rather than being cropped to fill it.

26.121 Empty Preview

Before generation, the Preview displays:

Your creation will appear here

with:

“Fill in the prompt and settings on the left to start generating.”

26.122 Current Result Actions

When a result exists, two controls appear near its upper-right area:

  1. Download
  2. Regenerate


26.123 Download Current Result

Select the Download icon to save the current generated Image.

26.124 Current Result Filename

The direct result Download requests a filename in this pattern:

ai-suite-gen-[timestamp].png.

26.125 Current Output Is Downloaded as PNG

The direct Download action names the current result with a:

.png

extension.

26.126 Download Started

The current result Download immediately displays:

Download started.

26.127 Download Uses the Shared Asset Helper

The underlying helper attempts to retrieve the generated asset through AIUNIFY's Download proxy and save it as a browser Blob.

If that fails, it opens the asset URL in a new tab.

26.128 Download Can Fall Back to a Browser Tab

If clicking Download opens an Image in a new tab instead of saving the file directly, the shared Download fallback likely occurred.

Use your browser's normal Save function when appropriate.

26.129 Regenerate Control

Beside Download is a Refresh-style control.

Selecting it calls the same:

handleGenerate

workflow again.

26.130 Regenerate Uses the Current Inputs

The regeneration action uses the current:

  1. Prompt
  2. Product Reference
  3. Avatar Reference
  4. Size
  5. Other values currently included in the request

It creates a new generation task.

26.131 Regenerate Is Not an Edit

Regenerate does not send the current generated Image back as an image-editing input.

It simply runs another Text-to-Image request based on the current generation inputs.

26.132 Current Result Is Cleared During Regeneration

Because handleGenerate clears resultImage at the beginning of every run, selecting Regenerate removes the current Preview while the replacement Image is being generated.

26.133 Preserve Good Results Before Regenerating

Before selecting Regenerate:

  1. Download a good result.
  2. Confirm it appears in Generation History.

This reduces the chance of losing easy access to an approved version.

26.134 No Confirmation Before Regeneration

The current Refresh control immediately starts another generation.

There is no source-verified confirmation dialog.

26.135 Regeneration Can Represent Additional AI Usage

Because Regenerate launches another full media-generation task, treat it as a new generation operation rather than a free Preview refresh.

26.136 Clicking the Current Result

The current Image itself is clickable and attempts to open Asset Viewer.

26.137 Current-Result Viewer Wiring Has a Limitation

When you click the current result, the component sets:

viewerIndex = 0

but the Asset Viewer receives:

recentImages

rather than a one-item array containing resultImage.

26.138 What This Means Operationally

The current result click relies on the first item in Generation History being the desired current Image.

If the backend's asset ordering does not place the newest result first, Asset Viewer could open a different Image.

26.139 If the Wrong Image Opens

If clicking the current large result opens the wrong historical Image:

  1. Close Asset Viewer.
  2. Locate the desired Image in Generation History.
  3. Click that specific historical Card.

This uses its exact History index.

26.140 Generation History

Below the main generator is:

Generation History.

26.141 Image History Loads Automatically

When the authenticated Image Generator opens, it requests:

list-assets&type=image.

26.142 Image History Is Type-Specific

Unlike Marketing Studio's eight-item mixed Image/Video recent view, Image Generator requests only assets with:

type=image.

26.143 No Eight-Item Slice Is Applied by This Page

The Image Generator sets the returned Image array directly as:

recentImages.

It does not apply the central Marketing Studio Dashboard's eight-asset limit.

26.144 Service Ordering Determines History Order

The client does not perform its own date Sort on the returned Image array.

The visible History order depends on the order returned by the Marketing service.

26.145 History Refreshes After Successful Generation

After polling reports success, Image Generator automatically runs:

fetchRecentImages().

The newly created asset can therefore appear in Generation History without requiring the subscriber to reload the page manually.

26.146 No History Found

If no Image assets are returned, the current message is:

No history found.

26.147 History Uses Marketing Asset Cards

Each historical Image is displayed using the shared:

MarketingAssetCard.

26.148 History Card Information

Each Image History Card can display:

  1. Image Preview
  2. Type badge
  3. Stored Prompt
  4. Relative creation time


26.149 Image Type Badge

The Card converts the Image asset Type into uppercase, typically:

IMAGE.

26.150 Historical Prompt

The stored Prompt appears beneath the Image.

If there is no Prompt, the fallback is:

No prompt provided.

26.151 Relative Creation Time

History Cards use the stored created_at timestamp to display relative time.

26.152 Hover Actions on Historical Images

Hovering over a History Card exposes:

  1. View
  2. Download
  3. Copy Link


26.153 No Delete in Image Generation History

Although MarketingAssetCard can support Delete when an onDelete callback is supplied, Image Generator does not pass one to its History Cards.

Therefore:

Image Generation History does not currently expose Delete.

26.154 No Rename in History

There is no source-verified:

  1. Rename Image
  2. Edit asset Name

control.

26.155 No Search History

There is no:

Search Images

field in Generation History.

26.156 No History Filter

Since the page already requests only Image assets, no separate user filter is exposed.

26.157 No History Sort

There is no subscriber-facing sort control.

26.158 No Folders or Tags

Generation History does not establish:

  1. Folders
  2. Collections
  3. Tags
  4. Campaign grouping

26.159 Viewing a Historical Image

Click the Image Card or its Eye control.

The page stores the selected History index and opens Asset Viewer.

26.160 Asset Viewer

The shared Asset Viewer opens the selected Image in a dark full-screen/lightbox-style environment.

26.161 Image Zoom

Asset Viewer loads the Zoom plugin.

This allows closer inspection of generated Images.

26.162 Use Zoom for Quality Assurance

Inspect:

  1. Eyes
  2. Hands
  3. Product labels
  4. Logo forms
  5. Small text
  6. Background details
  7. Edge artifacts
  8. Reflections

before approving an Image.

26.163 Download Historical Image

The MarketingAssetCard Download action saves an Image using a Name in this pattern:

marketing-image-[first 8 characters of asset ID].png.

26.164 Direct Result vs. History Download Names

The two Download paths use different filename patterns.

Current Result

ai-suite-gen-[timestamp].png

Generation History

marketing-image-[asset-id].png

26.165 Copy Historical Image Link

The History Card also provides a Share-style control that copies the asset URL.

26.166 Copy Confirmation

The exact notification is:

Link copied to clipboard.

26.167 Copy Link Does Not Copy the Prompt

The Share-style action copies:

asset.url

not the Image Prompt.

26.168 No Copy Prompt Control

There is no dedicated:

Copy Prompt

button on the History Card.

26.169 Asset Link Is Not a Newly Generated Share Link

The system simply copies the currently stored asset URL.

It does not create:

  1. Expiration
  2. Password
  3. Share permission
  4. Public-share record

26.170 Download Important Images Instead of Relying Only on URLs

For approved business creative, download the actual file.

A remote media URL should not automatically be treated as permanent business storage.

26.171 Persistence

Generation History is retrieved from the Marketing service rather than being stored only in the current React page state.

This establishes persistent Image Asset history across page visits, subject to the service retaining the record.

26.172 Generated Image Is Saved Through the Marketing Asset Workflow

The client does not display a separate:

Save Image

button after successful generation.

Instead, success triggers a History refresh, showing that generated media is handled through the Marketing Asset service.

26.173 No Manual Save Button

Because persistence is tied to the generator/service workflow, there is no visible:

Save to History

action.

26.174 No Unsaved-Draft Concept for Generated Images

The generated media result is not managed like Website Builder or Game Developer project drafts.

The system operates around generated Marketing Assets.

26.175 Current Result Still Should Be Downloaded When Important

Even with History, download approved production assets.

This gives you an independent copy for:

  1. Marketing campaigns
  2. Website upload
  3. Email
  4. Social media
  5. Brochures
  6. Client delivery

26.176 Marketing Image Token Reference

The general PROS SUITE Feature catalogue currently lists:

Marketing Image Gen — 50 Tokens.

26.177 Important Token Qualification

The Image Generator page itself does not display:

50 Tokens

beside Generate Masterpiece.

It also does not contain a direct client-side PROS SUITE Token-deduction call.

Final accounting occurs outside this sanitized client bundle.

Therefore:

50 Tokens is a source-verified feature catalogue/default reference, not proof that every current production Image request is permanently fixed at exactly 50 Tokens.

26.178 Provider Credits May Also Matter

The page explicitly recognizes a provider Error containing:

credits insufficient.

Accordingly, specialized media-provider availability can be a separate operational consideration from the account's displayed Monthly Tokens.

26.179 No Token Balance Is Displayed Inside the Image Generator

The specialized Image page does not display:

  1. Current Monthly Token balance
  2. Exact request price
  3. Token cost breakdown

inside the generation Card.

Use the normal PROS SUITE Monthly Tokens display for account-level monitoring.

26.180 No User Refresh Call After Image Success

Unlike the shared text-generation hook, the Image Generator's successful polling path refreshes the Image History but does not call the shared refreshUser() account function in this client source.

Therefore, the Sidebar Token display is not source-verified to refresh immediately as a direct consequence of Image completion without some other account refresh/navigation event.

26.181 Image Generator Does Not Use the Header LLM Selector

Because no selectedModel value is read or submitted, changing between normal PROS SUITE language Models should not be documented as the current method for choosing the Image model.

26.182 Image Generator Does Not Use Subscriber BYOK Headers

The current media request does not forward the provider API-Key headers described in Chapter 11.

The specialized Marketing generation service controls this workflow from the client perspective.

26.183 No Provider Configuration Inside Image Generator

There is no user-facing:

  1. Kie.ai API Key
  2. Image Provider selector
  3. Provider account
  4. Model version

field inside the current workspace.

26.184 Best Practice — Start With a Clear Creative Objective

Before generating, decide whether the Image is intended for:

  1. Brand awareness
  2. Product marketing
  3. Sales enablement
  4. Event promotion
  5. Website visual
  6. Social advertisement
  7. Educational content

Then write the Prompt accordingly.

26.185 Best Practice — Describe One Primary Concept

Avoid combining too many unrelated scenes into a single Prompt.

A focused Prompt generally gives the generator a clearer visual target.

26.186 Best Practice — Describe Subject Hierarchy

If the Product must dominate the composition, say:

“The Product is the clear hero and occupies the center foreground.”

If the Avatar is primary:

“The spokesperson is the main subject, with the Product clearly visible in their hands.”

26.187 Best Practice — Reinforce Important Style in the Prompt

Because the visible Style dropdown is not currently transmitted in the generation request, repeat the desired style in the Prompt.

Example:

“Cinematic commercial photography, realistic materials, dramatic lighting.”

26.188 Best Practice — Treat Resolution Choices as Ratios

Choose:

  1. 1:1
  2. 3:2
  3. 2:3

based on composition.

Do not assume the selector guarantees a particular pixel output.

26.189 Best Practice — Use the Correct Ratio Before Generation

Changing the ratio afterward does not crop or transform the already generated Image through a source-verified editing workflow.

Choose the desired format before selecting Generate.

26.190 Best Practice — Use Product References for Brand Continuity

When advertising an actual Product:

  1. Upload a clean Product Image.
  2. Select it.
  3. Describe how it should appear.
  4. Generate.
  5. Verify Product fidelity.

26.191 Best Practice — Use High-Quality Product References

A useful source Product Image should ideally have:

  1. Good lighting
  2. High visibility
  3. Minimal obstruction
  4. Correct branding
  5. Adequate resolution

26.192 Best Practice — Verify Product Fidelity

Even when using a reference, compare the generated result with the actual Product.

Check:

  1. Shape
  2. Labels
  3. Buttons
  4. Packaging
  5. Color
  6. Logo

26.193 Best Practice — Use AI Avatars Consistently

For campaign continuity, use the same approved Avatar across related creative where appropriate.

26.194 Best Practice — Verify Avatar Identity

Compare:

  1. Facial features
  2. Hair
  3. Skin tone
  4. Overall identity
  5. Clothing where relevant

before publishing.

26.195 Best Practice — Inspect Hands and Product Interaction

AI media often struggles when a person is:

  1. Holding a Product
  2. Pointing
  3. Typing
  4. Gripping objects

Zoom in before approval.

26.196 Best Practice — Specify Negative Requirements in Natural Language

Without a dedicated Negative Prompt field, use clear Prompt instructions such as:

“No text, no watermark, no extra fingers, no blue lighting.”

Results are still generative, so verify rather than assume compliance.

26.197 Best Practice — Do Not Put Confidential Information in Prompts

Avoid entering:

  1. Passwords
  2. API Keys
  3. Private customer information
  4. Confidential business records

into creative generation Prompts.

26.198 Best Practice — Download Before Regenerating

A good workflow is:

Generate

→ Inspect

→ Download if approved

→ Then Regenerate if another version is needed

26.199 Best Practice — Use History for Variations

Instead of treating Regenerate as overwriting the creative concept, use Generation History to compare multiple outputs.

26.200 Best Practice — Download the Winning Variation

Once you choose the strongest Image, preserve it outside PROS SUITE using Download.

26.201 Best Practice — Rename Downloaded Files

Current generated Names are system-oriented.

Rename important assets externally.

For example:

AIUNIFY_Enterprise_Campaign_Hero_01.png

26.202 Best Practice — Maintain External Versioning

For marketing production:

  1. hero-v1.png
  2. hero-v2.png
  3. hero-approved.png

can make campaign management easier.

26.203 Best Practice — Check Commercial Readiness

Before publishing, review:

  1. Subject quality
  2. Product accuracy
  3. Brand accuracy
  4. Written text
  5. Watermarks
  6. Logos
  7. Background artifacts
  8. Composition
  9. Legal/usage appropriateness

26.204 Best Practice — Do Not Treat Safety Acceptance as Marketing Approval

A Prompt passing the AI safety filter does not mean the Image has been:

  1. Brand-approved
  2. Legally approved
  3. Fact-checked
  4. Quality-assured

Those reviews remain separate.

26.205 Best Practice — Review Third-Party or Brand References Carefully

If the creative uses recognizable brands or other intellectual property, make sure your intended use is appropriate.

26.206 Troubleshooting — Cannot Open Image Generator

Check:

  1. You are signed into PROS SUITE.
  2. AI Marketing is visible.
  3. Image Generator is available to your account.

The current Image page itself redirects unauthenticated users to Login.

26.207 Troubleshooting — Generate Masterpiece Does Nothing

Check the Prompt.

If it is empty, the current system displays:

Please enter a prompt.

26.208 Troubleshooting — Prompt Cannot Be Edited

The Prompt is intentionally disabled while generation is active.

Wait until the current task succeeds or fails.

26.209 Troubleshooting — My Style Selection Is Not Changing the Result

The current client does not send the Style state in the generation request.

Write the desired style explicitly in your Prompt.

26.210 Troubleshooting — I Selected 3D Render but Got a Different Style

Again, reinforce:

“3D render”

or the detailed desired aesthetic in the Prompt.

The dropdown alone is not currently source-verified to control the request.

26.211 Troubleshooting — Resolution Is Not 4K

The field labeled Resolution currently selects an output ratio/size:

  1. 1:1
  2. 3:2
  3. 2:3

It does not expose 4K or explicit pixel dimensions.

26.212 Troubleshooting — Cannot Choose 16:9

16:9 is not one of the current Image Generator size choices.

Use one of the verified available options.

26.213 Troubleshooting — Cannot Upload a General Reference Image

The current Image Generator does not provide a generic reference upload field.

Use:

Upload Product

for Product references or:

Avatar Studio / Select AI Avatar

for reusable person references.

26.214 Troubleshooting — Product Upload Rejects My PDF

Product Reference accepts Images.

Convert or extract the appropriate Product Image before uploading.

26.215 Troubleshooting — Product Does Not Appear After Upload

A successful upload refreshes the Product list.

If it does not appear:

  1. Confirm you saw Product uploaded successfully.
  2. Allow the list to refresh.
  3. Reload the generator if needed.

26.216 Troubleshooting — Product Name Is Wrong

The Name is derived from the uploaded filename.

Rename the source Image before uploading another Product reference.

26.217 Troubleshooting — Product Reference Is Distorted

Reference-guided generation is still generative.

Try:

  1. Cleaner Product Image
  2. More explicit Prompt
  3. Simplified scene
  4. Strong Product-placement wording

and regenerate.

26.218 Troubleshooting — No Avatars Found

Select:

New Avatar

and create one through Avatar Studio.

26.219 Troubleshooting — Avatar Looks Different

Reference consistency is not pixel-perfect.

Use an approved Avatar reference and simplify the scene where necessary.

26.220 Troubleshooting — Product and Avatar Do Not Interact Naturally

Make the interaction explicit.

Example:

“The spokesperson holds the Product naturally with both hands, Product facing the camera, realistic hand anatomy.”

26.221 Troubleshooting — Generation Stays on Creating Your Vision

The visual Progress bar is not actual provider progress.

The client continues checking task status every five seconds.

Wait for:

  1. Success
  2. Failure

rather than relying on the animation.

26.222 Troubleshooting — Progress Bar Reached 100% but No Image Appeared

The 30-second progress animation is cosmetic.

Actual completion is determined by the provider task status.

Continue waiting for the result or an Error message.

26.223 Troubleshooting — Cannot Stop Generation

The current Image Generator has no source-verified Cancel/Stop button.

26.224 Troubleshooting — Prompt Flagged by AI Safety Filter

The current interface tells you to rephrase and avoid problematic:

  1. Real-person
  2. Brand
  3. Sensitive-topic

references where applicable.

Revise the Prompt rather than retrying it unchanged.

26.225 Troubleshooting — Credits Insufficient

This message comes from the specialized media generation path.

It can reflect provider/service credit availability and should not automatically be interpreted as the same thing as your PROS SUITE Monthly Token balance.

26.226 Troubleshooting — Generation Failed

Try:

  1. Simplify the Prompt.
  2. Remove potentially conflicting instructions.
  3. Remove a reference asset temporarily.
  4. Try another creative concept.
  5. Retry when service availability is restored.

26.227 Troubleshooting — Unexpected Response From Server

This indicates the generator did not receive a response in the expected format.

Retry after confirming your session/network remains active.

26.228 Troubleshooting — Current Image Disappeared When I Regenerated

That is current behavior.

Starting another generation clears the current result while the new task runs.

Use History or Download to preserve approved output first.

26.229 Troubleshooting — Clicking Current Result Opens Another Image

The current Preview's Viewer is wired to History index 0 rather than directly to the current result URL.

Open the specific Image from Generation History instead.

26.230 Troubleshooting — Cannot Delete a Historical Image

Image Generator does not pass a Delete action into its Generation History Cards.

No Delete control is currently available there.

26.231 Troubleshooting — Cannot Rename Historical Image

No Rename function is established.

Rename downloaded files externally.

26.232 Troubleshooting — Cannot Search History

No Search control exists in current Generation History.

26.233 Troubleshooting — Download Opened a New Tab

The Download helper falls back to opening the asset URL if direct proxy Download fails.

Save the file from the browser where appropriate.

26.234 Troubleshooting — Copy Link Did Not Copy the Image

Copy Link copies the asset URL as Text.

It does not copy the Image pixels to the clipboard.

26.235 Troubleshooting — Header Model Change Had No Effect

The Image Generator client does not submit the shared selectedModel.

This media generator is separate from the standard language-Model workflow.

26.236 Troubleshooting — My OpenAI/Anthropic/Gemini Key Did Not Change Image Generation

The current Image Generator does not send the subscriber's normal provider-key headers to the specialized Marketing API.

Those BYOK settings are not source-verified as controlling this Tool.

26.237 Image Generation Preparation Checklist

Before generating:

  1. I entered a clear Prompt.
  2. I identified the main subject.
  3. I described the desired composition.
  4. I described the lighting.
  5. I specified brand colors.
  6. I stated the intended marketing use.
  7. I selected the correct Product Reference if needed.
  8. I selected the correct AI Avatar if needed.
  9. I selected Square, Landscape, or Portrait.
  10. I stated critical visual style directly in the Prompt.
  11. I understand the Style dropdown is not currently source-verified to affect generation.
  12. I understand Resolution is a ratio selector, not pixel dimensions.

26.238 Product Reference Checklist

  1. My Product file is an Image.
  2. The filename is descriptive.
  3. Product is clearly visible.
  4. Product upload succeeded.
  5. Correct Product is selected.
  6. I stated how Product should appear.
  7. I understand the Product may still be altered by generative AI.

26.239 Avatar Reference Checklist

  1. I have an Avatar available.
  2. Correct Avatar is selected.
  3. I stated the intended pose/role.
  4. If using a Product too, I described the interaction.
  5. I will verify identity consistency in the final Image.

26.240 Generation Checklist

During processing:

  1. I recognize Generating...
  2. I recognize Creating your vision...
  3. I understand Kie.ai is identified as the current media-processing service.
  4. I understand status is checked automatically every five seconds.
  5. I understand the 30-second progress animation is not actual completion progress.
  6. I understand there is no Stop Generation control.
  7. I wait for success or failure.

26.241 Final Image Review Checklist

After completion:

  1. Main subject is correct.
  2. Product is accurate.
  3. Avatar looks consistent.
  4. Hands and anatomy are acceptable.
  5. Brand colors are correct.
  6. Written text is correct.
  7. Logos are correct.
  8. Background is clean.
  9. Composition matches the intended use.
  10. There are no unwanted watermarks.
  11. There are no obvious visual artifacts.

26.242 Preservation Checklist

Before starting another version:

  1. I confirmed the Image appears in Generation History.
  2. I downloaded the approved version.
  3. I renamed it if needed.
  4. I understand Regenerate starts a new generation.
  5. I understand the current result is cleared when a new task begins.

26.243 Generation History Checklist

You should now be able to:

  1. Find Generation History.
  2. Recognize historical Image thumbnails.
  3. View stored Prompt text.
  4. See relative creation time.
  5. Open an Image in Asset Viewer.
  6. Zoom the Image.
  7. Download an Image.
  8. Copy the Image URL.
  9. Understand there is no current Delete.
  10. Understand there is no Rename.
  11. Understand there is no Search.
  12. Understand there are no folders/tags.

26.244 Current Image-Generation Input Matrix

InputCurrent Support
Text PromptYes
Product ReferenceYes
Upload Product ImageYes
AI Avatar ReferenceYes
Product + Avatar TogetherYes
Generic Reference Image UploadNo dedicated control
PDF InputNo
DOCX InputNo
Negative Prompt FieldNo
SeedNo
Guidance ScaleNo
Number of ImagesNo
Inpainting MaskNo

26.245 Current Size Matrix

Visible ChoiceSent Value
Square1:1
Landscape3:2
Portrait2:3

The current client sends this value under the generation request's size option.

26.246 Current Style Matrix

Visible StyleUI AvailableSent in Current Generation Request
PhotorealisticYesNo source-verified transmission
Digital ArtYesNo source-verified transmission
CinematicYesNo source-verified transmission
3D RenderYesNo source-verified transmission

The Style value exists in client state but is absent from the current generation-request body.

26.247 Current Result Actions Matrix

ActionSupported
View ResultYes
DownloadYes
RegenerateYes
Edit ImageNo
CropNo
Resize Existing ResultNo
Remove BackgroundNo
InpaintNo
Save ButtonNo separate button
PublishNo

26.248 Generation History Actions Matrix

ActionSupported
ViewYes
ZoomYes
DownloadYes
Copy URLYes
View PromptYes
DeleteNo current Image History control
RenameNo
SearchNo
SortNo user control
TagNo
FolderNo

26.249 What Image Generator Currently Supports

The current subscriber-facing source verifies:

Prompting

  1. Text Prompt
  2. Required Prompt validation

Reference Inputs

  1. Reusable Product Reference
  2. Product Image Upload
  3. Reusable AI Avatar
  4. Product + Avatar generation

Output Shape

  1. 1:1
  2. 3:2
  3. 2:3

Visible Style UI

  1. Photorealistic
  2. Digital Art
  3. Cinematic
  4. 3D Render

Generation

  1. Specialized Marketing media API
  2. Automatic enhancement flag
  3. Asynchronous Task ID
  4. 5-second polling
  5. Kie.ai processing indicator
  6. Safety-filter handling
  7. Provider credit-error handling
  8. Success/failure states

Current Result

  1. Preview
  2. Download
  3. Regenerate

Persistence

  1. Type-specific Generation History
  2. Automatic History refresh after success

Historical Asset Management

  1. Asset Viewer
  2. Zoom
  3. Download
  4. Copy Link
  5. Prompt display
  6. Relative creation date

26.250 What Image Generator Does Not Currently Establish

The current source does not establish:

  1. Generic image-to-image upload
  2. Direct editing of an existing generated Image
  3. Inpainting
  4. Outpainting
  5. Mask editing
  6. Background removal
  7. Crop Tool
  8. Existing Image resize
  9. Exact pixel-resolution selector
  10. 4K selector
  11. 16:9 Image setting
  12. 9:16 Image setting
  13. Negative Prompt field
  14. Seed
  15. Guidance Scale
  16. Steps
  17. Batch quantity
  18. Multiple result selection
  19. Stop Generation
  20. Cancel Generation
  21. Generation timeout control
  22. Image Model selector
  23. Header LLM control over Image generation
  24. Subscriber provider API-Key forwarding
  25. Manual Save button
  26. Delete from Image History
  27. Rename
  28. Search
  29. Sort
  30. Folders
  31. Tags
  32. Publish
  33. Public share permissions
  34. Fixed guaranteed 50-Token live charge

26.251 Important Current-Version Findings

Several Image Generator behaviors deserve particular attention.

Style Selector Is Not Wired Into the Current Request

The Style dropdown is visible, but the selected value is not included in the current Marketing API request.

Use the Prompt to express important style requirements.

Resolution Is an Aspect/Size Selector

The current choices are 1:1, 3:2, and 2:3 rather than pixel dimensions.

Generation Uses a Specialized Media Path

The Tool calls /api/marketing, not the shared text-generation AI stream.

Shared Header Model Is Not Sent

The selected PROS SUITE language Model is not part of this client's request.

BYOK Provider Keys Are Not Sent

Normal subscriber provider-key headers are absent from the Image-generation client call.

Generation Is Asynchronous

A task is created and polled every five seconds.

The Visible Progress Bar Is Cosmetic

Its 30-second animation does not represent actual task completion.

No Stop Button Exists

The subscriber waits for success/failure after the request begins.

Image History Persists

After successful generation, the generator refreshes its Image-specific History.

26.252 Recommended Professional Image Workflow

Use the current Image Generator in this order:

IMAGE GENERATOR

Write:

PROMPT

Optional:

SELECT PRODUCT REFERENCE

Optional:

SELECT AI AVATAR

Choose:

SQUARE / LANDSCAPE / PORTRAIT

Choose visible Style

and also:

WRITE THE STYLE INTO THE PROMPT

GENERATE MASTERPIECE

Wait:

CREATING YOUR VISION...

Automatic status polling

IMAGE GENERATED SUCCESSFULLY!

Inspect Current Result

Open/Zoom when needed

DOWNLOAD

Review:

GENERATION HISTORY

Create another version with:

REGENERATE

Compare variations

Download the approved final Image.

26.253 Recommended Campaign Workflow

For a Product campaign:

UPLOAD CLEAN PRODUCT REFERENCE

Select Product

Optional Avatar

Prompt:

Campaign Goal + Subject + Environment + Product Placement + Brand Colors + Composition + Lighting + Style

Select ratio

Generate

Inspect Product fidelity

Download approved variation

Regenerate additional variations

Use Generation History to compare outputs

Select final campaign creative.

26.254 Chapter Summary

AIUNIFY PROS SUITE Image Generator is the specialized AI Marketing Tool at:

/ai-marketing/image-generator

and is presented inside the workspace as:

Text-to-Image Generator

with:

“Create stunning marketing visuals with AI.”

Subscribers begin with the Imagine... Prompt field and can optionally select reusable:

  1. Product References
  2. AI Avatars

Product References can be uploaded as Images and then reused through the Product Picker. The uploaded Product Name is derived from its filename. AI Avatars are retrieved from Avatar Studio and can likewise be reused.

When a Product is selected, the generator adds its Image URL to the generation references and instructs the AI to feature the Product prominently. When an Avatar is selected, it instructs the AI to include that person as the main character. When both are selected, it additionally asks for the person to interact naturally with or showcase the Product.

The current Resolution selector provides:

  1. Square 1:1
  2. Landscape 3:2
  3. Portrait 2:3

but does not expose actual pixel dimensions.

The current Style selector visually offers:

  1. Photorealistic
  2. Digital Art
  3. Cinematic
  4. 3D Render

but the current generation request does not submit the selected style value. Therefore, important style requirements should be stated directly in the Prompt rather than relying on the dropdown alone.

Selecting Generate Masterpiece submits a specialized Marketing request using:

  1. Final Prompt
  2. Selected size
  3. isEnhance: true
  4. Product/Avatar reference URLs

The request does not include the normal shared PROS SUITE selected language Model or the subscriber's standard provider API-Key headers.

Generation is asynchronous. A successful start returns a Task ID, after which the client polls approximately every five seconds. While processing, the page says:

“Creating your vision...”

and:

“Kie.ai is processing your high-resolution marketing image.”

The visible Progress animation lasts 30 seconds, but it is not tied to provider task progress and should not be interpreted as an exact completion percentage.

Successful completion produces:

Image generated successfully!

The first returned result URL becomes the current Image and Generation History is automatically refreshed.

The current result provides:

  1. Download
  2. Regenerate

The direct Download uses a filename such as:

ai-suite-gen-[timestamp].png

while historical Image Cards use names such as:

marketing-image-[asset-id].png.

Image Generator also provides persistent:

Generation History

retrieved from the Marketing asset service. Historical Images can be:

  1. Viewed
  2. Zoomed
  3. Downloaded
  4. Copied by URL

but the current Image History does not provide Delete, Rename, Search, folders, or tags.

The generic PROS SUITE feature catalogue currently references 50 Tokens for Marketing Image generation. However, the Image Generator itself does not display a fixed 50-Token charge, and the final media-service billing/accounting logic is outside the sanitized subscriber source. The page also recognizes a separate provider Error for credits insufficient, so provider availability and PROS SUITE Tokens should not automatically be treated as the same accounting mechanism.

The recommended operating principle is:

Write a Precise Prompt → Select Product and/or Avatar References When Needed → Choose the Correct Image Ratio → Put Critical Style Instructions Directly in the Prompt → Generate → Wait for True Completion Rather Than the Cosmetic Progress Bar → Inspect the Image at Full Size → Verify Product, Avatar, Text, and Branding → Download Approved Results → Use Generation History to Compare Variations → Regenerate Only When You Intend to Create Another Full Image.

Write Your Comment