# Workflow Action – AI Image Generation > Learn how to use AI Image Generation in GHL Customer Care workflows to create images, choose models and quality, apply brand settings, and access generated image URLs. - Source: https://docs.ghlcustomercare.com/docs/workflows/workflow-ai-workflow-actions/workflow-action-ai-image-generation - Section: Workflows / Workflow AI Workflow Actions - Reading time: 12 min - Images: 16, each explained below --- This article explains how to use the AI Image Generation action in workflows to create images with AI. You’ll find step-by-step configuration instructions, details on available models and settings, how to access the generated image, practical use cases, and answers to common questions. **Note:** This is a **premium** **action**. Using this action will incur additional charges per execution. --- **TABLE OF CONTENTS** - [What is AI Image Generation Action in Workflows?](#what-is-ai-image-generation-action-in-workflows)[](#key-benefits-of-ai-image-generation-action) - [Key Benefits of AI Image Generation Action](#key-benefits-of-ai-image-generation-action)[](#action-details) - [Action Details](#action-details)[](#how-to-use-the-ai-image-generation-action) - [How to Use the AI Image Generation Action](#how-to-use-the-ai-image-generation-action)[](#how-to-access-the-generated-images) - [How to Access the Generated Images](#how-to-access-the-generated-images)[](#use-cases) - [Use Cases](#use-cases)[](#tips-for-better-results) - [Tips for Better Results](#tips-for-better-results)[](#pricing) - [Pricing](#pricing)[](#frequently-asked-questions) - [Frequently Asked Questions](#frequently-asked-questions)[](#related-articles) - [Related Articles](#related-articles) --- # **What is AI Image Generation Action in Workflows?** The AI Image Generation action, available under AI Actions in Workflows, lets you generate images using AI models directly inside your automation. You provide a text prompt describing the image you want, choose a model and quality level, and the action returns a generated image stored at a publicly accessible URL. Generated images are saved automatically in Media Storage and are available as variables in downstream actions – so you can attach them to emails, send them over SMS, post them to social channels, or pass them to external systems. --- ## **Key Benefits of AI Image Generation Action** - **Multiple AI Models:** Choose from a range of image models to match your quality, style, and speed requirements. - **Prompt Enhancement:** Refine a rough prompt into a detailed one with a single click, producing noticeably better output. - **Ready-to-Use Templates:** Start from a pre-written prompt for common formats like product mockups, social posts, promo flyers, and lifestyle imagery. - **Brand Consistency:** Apply your existing Design Kit and Brand Voice to keep generated images aligned with your brand. - **Dynamic Prompts:** Build prompts from custom values so each contact, product, or webhook payload produces a different image. - **Automatic Storage:** Every generated image is saved to Media Storage at a publicly accessible URL, ready to use anywhere. --- ## **Action Details**
FieldDescription
Action NameA custom name for the action, used to identify it on the workflow canvas and in execution logs.
ModelThe AI model used to generate the image. See the Model options list below.
QualityThe generation quality level. Options are Auto (default), High, Medium, and Low.
Prompt A text description of the image you want to generate. Supports custom values, so you can build dynamic prompts from contact fields, webhook data, or previous action outputs.
TemplatesPre-written prompts for common image types. Selecting one pre-fills the prompt field, which you can then edit.
Additional Settings
Optional controls for size, background, output format, Design Kit, and Brand Voice. See the Additional Settings section below.
--- ## **How to Use the AI Image Generation Action** ### **Step 1:** Add the Action 1. Go to **Automation** > **Workflows**. 2. **Create** a new **workflow** or **edit** an **existing** one. ![Step 2 of 3: Create a new workflow or edit an existing one](https://jumpshare.com/share/sdAZAU36nE7nJWCjV65F+/Screen+Shot+2026-08-26+at+16.44.40.png) **Step 2 of 3: Create a new workflow or edit an existing one** This screenshot accompanies step 2 of 3 in the "Step 1: Add the Action" section of "Workflow Action – AI Image Generation". At this point in the walkthrough you create a new workflow or edit an existing one. The navigation path used here is Automation > Workflows. The next step is to in your workflow, click the + icon to add a new action, then find AI Image Generation under AI Actions and select it. Give the action a clear, descriptive name so it’s easy to identify on the canvas. - Path: Automation > Workflows - What this covers: Create a new workflow or edit an existing one. - Controls: Create, workflow, edit, existing, Automation, Workflows, +, add, new, action, AI Image Generation, under AI Actions - Next: In your workflow, click the + icon to add a new action, then find AI Image Generation under AI Actions and select it. Give the action a clear, descriptive name so it’s easy to identify on the canvas. Full procedure: 1. Go to Automation > Workflows. 2. Create a new workflow or edit an existing one. <- this image 3. In your workflow, click the + icon to add a new action, then find AI Image Generation under AI Actions and select it. Give the action a clear, descriptive name so it’s easy to identify on the canvas. 3. In your workflow, click the **+** icon to **add** a **new** **action**, then find **AI Image Generation** **under AI Actions** and select it. Give the action a clear, descriptive name so it’s easy to identify on the canvas. ![Step 3 of 3: In your workflow, click the + icon to add a new action, then find AI…](https://jumpshare.com/share/IC3WjmPC4gIkKKAAp4Bu+/GIF+Recording+2026-08-26+at+16.48.31.gif) **Step 3 of 3: In your workflow, click the + icon to add a new action, then find AI…** This animation accompanies step 3 of 3 in the "Step 1: Add the Action" section of "Workflow Action – AI Image Generation". At this point in the walkthrough you in your workflow, click the + icon to add a new action, then find AI Image Generation under AI Actions and select it. Give the action a clear, descriptive name so it’s easy to identify on the canvas. The navigation path used here is Automation > Workflows. - Path: Automation > Workflows - What to choose: In your workflow, click the + icon to add a new action, then find AI Image Generation under AI Actions and select it. Give the action a clear, descriptive name so it’s easy to identify on the canvas. - Controls: +, add, new, action, AI Image Generation, under AI Actions, Automation, Workflows, Create, workflow, edit, existing Full procedure: 1. Go to Automation > Workflows. 2. Create a new workflow or edit an existing one. 3. In your workflow, click the + icon to add a new action, then find AI Image Generation under AI Actions and select it. Give the action a clear, descriptive name so it’s easy to identify on the canvas. <- this image ### **Step 2:** Select the Model Inside the prompt section, **choose the AI model you want to use for generation**. The following models are available: - GPT Image 2 - Gemini 3 Pro Image (Nano Banana Pro) - Gemini 3.1 Flash Image (Nano Banana 2) - Gemini 2.5 Flash Image (Nano Banana) Different models produce different visual styles and handle text-in-image, photorealism, and composition differently. If you’re not sure which to pick, try the same prompt across two models and compare the output. ![Step 2: Select the Model (image 3 of 16)](https://jumpshare.com/share/14qfCsrYTrO9GwZFtzFl+/Screen+Shot+2026-08-26+at+17.03.15.png) **Step 2: Select the Model (image 3 of 16)** This screenshot appears in the "Step 2: Select the Model" section of "Workflow Action – AI Image Generation". The text alongside this image reads: Different models produce different visual styles and handle text-in-image, photorealism, and composition differently. If you’re not sure which to pick, try the same prompt across two models and compare the output. This part of the guide covers 4 fields, listed below. Immediately after, the guide continues: Click the quality selector to open the quality options. - What to choose: Different models produce different visual styles and handle text-in-image, photorealism, and composition differently. If you’re not sure which to pick, try the same prompt across two models and compare the output. - Fields: GPT Image 2, Gemini 3 Pro Image (Nano Banana Pro), Gemini 3.1 Flash Image (Nano Banana 2), Gemini 2.5 Flash Image (Nano Banana) - Next: Click the quality selector to open the quality options. Full procedure: 1. GPT Image 2 2. Gemini 3 Pro Image (Nano Banana Pro) 3. Gemini 3.1 Flash Image (Nano Banana 2) 4. Gemini 2.5 Flash Image (Nano Banana) ### **Step 3:** Set the Quality Click the **quality selector** to open the quality options.  By **default** this is set to **Auto**, which lets the system pick an appropriate level for your prompt. You can also explicitly choose **High, Medium, or Low**.  Higher quality produces more detailed images but takes longer to generate. ![Step 3: Set the Quality (image 4 of 16)](https://jumpshare.com/share/n0OWm7rz6KySFe7FV0JO+/Screen+Shot+2026-08-26+at+17.07.42.png) **Step 3: Set the Quality (image 4 of 16)** This screenshot appears in the "Step 3: Set the Quality" section of "Workflow Action – AI Image Generation". The text alongside this image reads: Higher quality produces more detailed images but takes longer to generate. Immediately after, the guide continues: In the prompt input box, describe the image you want to generate. - What this covers: Higher quality produces more detailed images but takes longer to generate. - Controls: quality selector, default, Auto, High, Medium, or Low - Next: In the prompt input box, describe the image you want to generate. ### **Step 4:** Write the Prompt In the prompt input box, **describe the image you want to generate**.  Be **specific** about the **subject, style, setting, lighting, and composition** – more detail generally produces better results. The **prompt field supports custom values**, so you can insert contact fields, webhook data, or output from previous actions to build dynamic prompts. Click the **Enhance Prompt** button above the prompt input box to have AI expand and refine what you’ve written. This adds detail around style, lighting, and composition that you might not have specified, and typically produces noticeably better output. You can edit the enhanced prompt further before saving. ![Step 4: Write the Prompt (image 5 of 16)](https://jumpshare.com/share/aB48kfaQ7HLajvYoSz8G+/Screen+Shot+2026-08-26+at+17.18.38.png) **Step 4: Write the Prompt (image 5 of 16)** This screenshot appears in the "Step 4: Write the Prompt" section of "Workflow Action – AI Image Generation". The text alongside this image reads: Click the Enhance Prompt button above the prompt input box to have AI expand and refine what you’ve written. This adds detail around style, lighting, and composition that you might not have specified, and typically produces noticeably better output. You can edit the enhanced prompt further before…. Immediately after, the guide continues: Instead of writing a prompt from scratch, you can start from one of four templates shown below the prompt box. - What to fill in: Click the Enhance Prompt button above the prompt input box to have AI expand and refine what you’ve written. This adds detail around style, lighting, and composition that you might not have specified, and typically produces noticeably better output. You can edit the enhanced prompt further before saving. - Controls: describe the image you want to generate, specific, prompt field supports custom values, Enhance Prompt - Next: Instead of writing a prompt from scratch, you can start from one of four templates shown below the prompt box: ### **Step 5:** Start From a Template (Optional) Instead of writing a prompt from scratch, you can start from one of four templates shown below the prompt box: - Product Mockups – Product shots and mockup presentations. - Social Post – Graphics sized and styled for social media feeds. - Promo Flyer – Promotional flyers and offer announcements. - Lifestyle – Lifestyle and in-context scene imagery. Clicking a template pre-fills the prompt field with a ready-written prompt for that format. You can then tweak it to match your specific requirement before saving. ![Step 5: Start From a Template (Optional) (image 6 of 16)](https://jumpshare.com/share/rSkmiZJFPyrLsRrtIDnu+/Screen+Shot+2026-08-26+at+17.56.38.png) **Step 5: Start From a Template (Optional) (image 6 of 16)** This screenshot appears in the "Step 5: Start From a Template (Optional)" section of "Workflow Action – AI Image Generation". The text alongside this image reads: Clicking a template pre-fills the prompt field with a ready-written prompt for that format. You can then tweak it to match your specific requirement before saving. Immediately after, the guide continues: You can attach up to five images to the action as visual context. These images are passed to the image model together with your prompt, so you can control the setting, the subject, or brand elements directly rather than describing them in…. - What this covers: Clicking a template pre-fills the prompt field with a ready-written prompt for that format. You can then tweak it to match your specific requirement before saving. - Next: You can attach up to five images to the action as visual context. These images are passed to the image model together with your prompt, so you can control the setting, the subject, or brand elements directly rather than describing them in words alone. Full procedure: 1. Product Mockups – Product shots and mockup presentations. 2. Social Post – Graphics sized and styled for social media feeds. 3. Promo Flyer – Promotional flyers and offer announcements. 4. Lifestyle – Lifestyle and in-context scene imagery. ### Step 6: Reference Images (Optional) You can attach up to five images to the action as visual context. These images are passed to the image model together with your prompt, so you can control the setting, the subject, or brand elements directly rather than describing them in words alone. **Adding Reference Images ** The Reference images section sits below the templates. Choose one of three sources:
SourceHow it works
System uploadUpload image files directly from your computer. Click to upload or drag and drop – you can select multiple files at once.
Media libraryBrowse and select images already stored in your Media Library.
URLEnter the URL of an image and click Add. This field supports custom values, so the URL can come from a previous action, a webhook payload, or a contact field.
### ![Step 6: Reference Images (Optional) (image 7 of 16)](https://s3.amazonaws.com/cdn.freshdesk.com/data/helpdesk/attachments/production/155080565421/original/aGPeiClbbBAnOOMmtrzbnYcVXCeSrBr4Lg.png) **Step 6: Reference Images (Optional) (image 7 of 16)** This screenshot appears in the "Step 6: Reference Images (Optional)" section of "Workflow Action – AI Image Generation". The text alongside this image reads: Source How it works System upload Upload image files directly from your computer. Click to upload or drag and drop – you can select multiple files at once. Media library Browse and select images already stored in your Media Library. URL Enter the URL of an image and click Add. This field supports…. Immediately after, the guide continues: Referring to Reference Images in Your Prompt. - What to fill in: Source How it works System upload Upload image files directly from your computer. Click to upload or drag and drop – you can select multiple files at once. Media library Browse and select images already stored in your Media Library. URL Enter the URL of an image and click Add. This field supports custom values, so the URL can come from a previous action, a webhook payload, or a contact field. - Next: Referring to Reference Images in Your Prompt **Referring to Reference Images in Your Prompt** Reference images are passed in the order you add them, and you can refer to them by position in your prompt – for example, “the location shown in the first reference image” or “the logo from the third reference image.” This lets you tell the model what role each image plays rather than leaving it to infer. **Example: Combining a Setting, a Subject, and a Logo** In this example three reference images were added – an environment, a person, and a brand logo – and the prompt describes how each should be used.
1.Setting

![Step 6: Reference Images (Optional) (image 8 of 16)](https://s3.amazonaws.com/cdn.freshdesk.com/data/helpdesk/attachments/production/155080565936/original/sgLlUSHbMaGATJ3aagjRVV_QqJh9459PFg.jpg) **Step 6: Reference Images (Optional) (image 8 of 16)** This screenshot appears in the "Step 6: Reference Images (Optional)" section of "Workflow Action – AI Image Generation". The text alongside this image reads: In this example three reference images were added – an environment, a person, and a brand logo – and the prompt describes how each should be used. Immediately after, the guide continues: The prompt then refers to each image by its position. - What this covers: In this example three reference images were added – an environment, a person, and a brand logo – and the prompt describes how each should be used. - Next: The prompt then refers to each image by its position:

2.Subject

![Step 6: Reference Images (Optional) (image 9 of 16)](https://s3.amazonaws.com/cdn.freshdesk.com/data/helpdesk/attachments/production/155080565979/original/W3ek6-Za6Z3K-mZIIJpiifcVL7GmbCjsYA.jpg) **Step 6: Reference Images (Optional) (image 9 of 16)** This screenshot appears in the "Step 6: Reference Images (Optional)" section of "Workflow Action – AI Image Generation". The text alongside this image reads: In this example three reference images were added – an environment, a person, and a brand logo – and the prompt describes how each should be used. Immediately after, the guide continues: The prompt then refers to each image by its position. - What this covers: In this example three reference images were added – an environment, a person, and a brand logo – and the prompt describes how each should be used. - Next: The prompt then refers to each image by its position:

3.Logo

![Step 6: Reference Images (Optional) (image 10 of 16)](https://s3.amazonaws.com/cdn.freshdesk.com/data/helpdesk/attachments/production/155080566296/original/UsRb7fc_lC8k_vcmBgv0dKq2uya4qrNayg.png) **Step 6: Reference Images (Optional) (image 10 of 16)** This screenshot appears in the "Step 6: Reference Images (Optional)" section of "Workflow Action – AI Image Generation". The text alongside this image reads: In this example three reference images were added – an environment, a person, and a brand logo – and the prompt describes how each should be used. Immediately after, the guide continues: The prompt then refers to each image by its position. - What this covers: In this example three reference images were added – an environment, a person, and a brand logo – and the prompt describes how each should be used. - Next: The prompt then refers to each image by its position:

**The prompt then refers to each image by its position:** _“A realistic image of a lady wearing a beautiful summer dress with light colors like blue and white, sitting in the location shown in the first reference image, looking directly into the camera with a smile. The scene captures her clearly and naturally within that setting. The logo from the third reference image is placed visibly in either the bottom left or bottom right corner of the image, fitting suitably with the overall composition.”_ ![Step 6: Reference Images (Optional) (image 11 of 16)](https://s3.amazonaws.com/cdn.freshdesk.com/data/helpdesk/attachments/production/155080566403/original/EpPY43gtsGvR70EHqwfwQWE_PX1NaY1Ppg.png) **Step 6: Reference Images (Optional) (image 11 of 16)** This screenshot appears in the "Step 6: Reference Images (Optional)" section of "Workflow Action – AI Image Generation". The text alongside this image reads: “A realistic image of a lady wearing a beautiful summer dress with light colors like blue and white, sitting in the location shown in the first reference image, looking directly into the camera with a smile. The scene captures her clearly and naturally within that setting. The logo from the third…. Immediately after, the guide continues: The generated image places the subject from the second reference into the setting from the first, with the logo from the third applied in the corner. - What this covers: “A realistic image of a lady wearing a beautiful summer dress with light colors like blue and white, sitting in the location shown in the first reference image, looking directly into the camera with a smile. The scene captures her clearly and naturally within that setting. The logo from the third reference image is placed visibly in either the bottom left or bottom right corner of the image, fitting suitably with the overall composition.” - Next: The generated image places the subject from the second reference into the setting from the first, with the logo from the third applied in the corner: The generated image places the subject from the second reference into the setting from the first, with the logo from the third applied in the corner: ![Step 6: Reference Images (Optional) (image 12 of 16)](https://s3.amazonaws.com/cdn.freshdesk.com/data/helpdesk/attachments/production/155080566482/original/Jn550VuchligJHe74QUvOTvLcmeCmSyC6Q.png) **Step 6: Reference Images (Optional) (image 12 of 16)** This screenshot appears in the "Step 6: Reference Images (Optional)" section of "Workflow Action – AI Image Generation". The text alongside this image reads: The generated image places the subject from the second reference into the setting from the first, with the logo from the third applied in the corner. Immediately after, the guide continues: Expand Additional Settings to fine-tune the output format and apply your brand assets. - What this covers: The generated image places the subject from the second reference into the setting from the first, with the logo from the third applied in the corner: - Next: Expand Additional Settings to fine-tune the output format and apply your brand assets. ### **Step 7:** Additional Settings (Optional) Expand Additional Settings to fine-tune the output format and apply your brand assets.
SettingDescription
SizeThe aspect ratio of the generated image – Square, Landscape, or Portrait. The exact pixel dimensions for each option are shown below the selector.
BackgroundWhether the generated image uses a transparent or opaque background. Defaults to Auto; you can also select Opaque. Transparent backgrounds are useful for logos, product cut-outs, and overlays.
Output FormatThe file format of the generated image – PNG, JPEG, or WebP. Use PNG for transparency, JPEG for smaller photo files, and WebP for web-optimized delivery.
Design KitApplies a Design Kit style from your account to guide the generated image, keeping visuals consistent with your existing design system.
Brand VoiceApplies your Brand Voice details to guide the generated image, providing the AI with additional brand context.
**Note:** [Design Kit](https://docs.ghlcustomercare.com/docs/marketing/brand-board/editing-a-design-kit) and [Brand Voice](https://docs.ghlcustomercare.com/docs/marketing/brand-board/brand-voice-in-brand-boards) options pull from the assets already set up in your account. If you haven’t configured them yet, set them up first and they’ll become selectable here. ### ![Step 7: Additional Settings (Optional) (image 13 of 16)](https://jumpshare.com/share/0gvamwqao9pVyKAhpjo9+/Screen+Shot+2026-08-26+at+18.01.29.png) **Step 7: Additional Settings (Optional) (image 13 of 16)** This screenshot appears in the "Step 7: Additional Settings (Optional)" section of "Workflow Action – AI Image Generation". The text alongside this image reads: Note: Design Kit and Brand Voice options pull from the assets already set up in your account. If you haven’t configured them yet, set them up first and they’ll become selectable here. Immediately after, the guide continues: Once your prompt and settings are configured, save the action. The generated image will be available as a variable in all downstream actions once the workflow executes. - What this covers: Note: Design Kit and Brand Voice options pull from the assets already set up in your account. If you haven’t configured them yet, set them up first and they’ll become selectable here. - Next: Once your prompt and settings are configured, save the action. The generated image will be available as a variable in all downstream actions once the workflow executes. ### **Step 8:** Save the Action Once your prompt and settings are configured, **save the action**. The generated image will be available as a variable in all downstream actions once the workflow executes. ![Step 8: Save the Action (image 14 of 16)](https://jumpshare.com/share/1bJv5BItQOjqmsNBUpqX+/Screen+Shot+2026-08-26+at+18.03.12.png) **Step 8: Save the Action (image 14 of 16)** This screenshot appears in the "Step 8: Save the Action" section of "Workflow Action – AI Image Generation". The text alongside this image reads: Once your prompt and settings are configured, save the action. The generated image will be available as a variable in all downstream actions once the workflow executes. Immediately after, the guide continues: Once the action executes, the generated image is available in two places. - How to confirm: Once your prompt and settings are configured, save the action. The generated image will be available as a variable in all downstream actions once the workflow executes. - Controls: save the action - Next: Once the action executes, the generated image is available in two places. --- ## **How to Access the Generated Images** Once the action executes, the generated image is available in two places. ### **1\. As Custom Values in Downstream Actions** In any action after the AI Image Generation step, open the custom value picker and navigate to AI Image Generation. Select the generated image to see three available values: - **Image URL:** The publicly accessible URL of the generated image. Opening this link displays the image directly, and you can download it from there. Use this value to attach the image to emails, send it over SMS/MMS, or pass it to an external system via web-hook. - **Image File Path:** The storage path of the generated image file. - **Image File Name:** The file name of the generated image. ![1. As Custom Values in Downstream Actions (image 15 of 16)](https://jumpshare.com/share/FocsM50SM5es4RBtZSWV+/GIF+Recording+2026-08-26+at+18.06.40.gif) **1. As Custom Values in Downstream Actions (image 15 of 16)** This animation appears in the "1. As Custom Values in Downstream Actions" section of "Workflow Action – AI Image Generation". The text alongside this image reads: Image URL: The publicly accessible URL of the generated image. Opening this link displays the image directly, and you can download it from there. Use this value to attach the image to emails, send it over SMS/MMS, or pass it to an external system via web-hook. Image File Path: The storage path of…. Immediately after, the guide continues: Every generated image is automatically saved to Media Storage. You can browse, download, and reuse these images from there at any time, just like any other uploaded asset – including in emails, funnels, websites, and social posts built…. - What this covers: Image URL: The publicly accessible URL of the generated image. Opening this link displays the image directly, and you can download it from there. Use this value to attach the image to emails, send it over SMS/MMS, or pass it to an external system via web-hook. Image File Path: The storage path of the generated image file. Image File Name: The file name of the generated image. - Next: Every generated image is automatically saved to Media Storage. You can browse, download, and reuse these images from there at any time, just like any other uploaded asset – including in emails, funnels, websites, and social posts built outside the workflow. Full procedure: 1. Image URL: The publicly accessible URL of the generated image. Opening this link displays the image directly, and you can download it from there. Use this value to attach the image to emails, send it over SMS/MMS, or pass it to an external system via web-hook. 2. Image File Path: The storage path of the generated image file. 3. Image File Name: The file name of the generated image. ### **2\. In Media Storage** Every generated image is **automatically saved to Media Storage**. You can browse, download, and reuse these images from there at any time, just like any other uploaded asset – including in emails, funnels, websites, and social posts built outside the workflow. ![2. In Media Storage (image 16 of 16)](https://s3.amazonaws.com/cdn.freshdesk.com/data/helpdesk/attachments/production/155079283565/original/exD52h52k3LNgtI54vmGtNuRfFgI7R_MfQ.png) **2. In Media Storage (image 16 of 16)** This screenshot appears in the "2. In Media Storage" section of "Workflow Action – AI Image Generation". The text alongside this image reads: Every generated image is automatically saved to Media Storage. You can browse, download, and reuse these images from there at any time, just like any other uploaded asset – including in emails, funnels, websites, and social posts built outside the workflow. Immediately after, the guide continues: Scenario: You want to produce quick product mockups or visual concepts to share with clients without waiting on a designer. Requests arrive from an external system – a Google Sheet, a form, or a partner platform – with a short description…. - What this covers: Every generated image is automatically saved to Media Storage. You can browse, download, and reuse these images from there at any time, just like any other uploaded asset – including in emails, funnels, websites, and social posts built outside the workflow. - Controls: automatically saved to Media Storage - Next: Scenario: You want to produce quick product mockups or visual concepts to share with clients without waiting on a designer. Requests arrive from an external system – a Google Sheet, a form, or a partner platform – with a short description of what’s needed. --- ## **Use Cases** ### **1\. Generating Product Mockups from Incoming Requests** **Scenario:** You want to produce quick product mockups or visual concepts to share with clients without waiting on a designer. Requests arrive from an external system – a Google Sheet, a form, or a partner platform – with a short description of what’s needed. **Setup:** - **Trigger:** Inbound Webhook (carrying the product description) - **Action 1:** AI Image Generation – Product Mockups template, with the incoming description inserted into the prompt as a custom value. Apply your Design Kit for brand consistency. - **Action 2:** Send Email – Include the Image URL so the client receives the mockup immediately. ### **2\. Personalized Campaign Visuals** Scenario: You want each contact in a campaign to receive a visual tailored to their interest, location, or purchase history – rather than one generic stock image for everyone. **Setup:** - **Trigger:** Contact Tag Added (e.g., “campaign-enrolled”) - **Action 1:** AI Image Generation – Build the prompt using contact custom values so the image reflects that contact’s segment. Apply Brand Voice for tone consistency. - **Action 2:** Send Email or MMS – Use the Image URL as the campaign visual. ### **3\. On-Demand Images from Conversations** **Scenario:** A customer interacting with your bot asks for a visual – a design concept, a room layout, a styled product shot. You want to generate and return it in the conversation without human involvement. Setup: - **Trigger:** Customer Replied / Conversation AI handoff - **Action 1:** AI Image Generation – Use the customer’s message content as the prompt input. - **Action 2:** Send SMS/MMS – Return the Image URL to the customer in the same conversation thread. **More Ideas** - **Social content pipelines:** Generate post graphics automatically whenever a new blog, offer, or announcement is published, so visuals keep pace with your content calendar. - **Promo and event flyers:** Produce flyers for recurring promotions, seasonal offers, or local events without a design request each time. - **Catalog and listing visuals:** Generate consistent lifestyle or white-background shots across a product range, useful where photography for every SKU isn’t practical. - **Creative variations for testing:** Produce several visual directions for the same campaign concept and test which performs best before committing to final production. - **Blog and article imagery:** Generate on-brand featured images as part of a content publishing workflow, replacing generic stock photography. --- ## **Tips for Better Results** - Be specific in your prompt. Describe the subject, style, setting, lighting, and mood rather than just naming the object. - Use Enhance Prompt when starting from a short or rough description – it fills in detail the model needs. - Apply Design Kit and Brand Voice for anything customer-facing, so output stays on-brand rather than generic. - Match Size to the destination – Square for social feeds, Landscape for email headers and banners, Portrait for stories and mobile. - Test your prompt on a few sample contacts before publishing a workflow that runs at volume. - Save prompts that work well. Reusing a proven prompt structure gives more consistent results than rewriting each time. --- ## **Pricing** Image generation is billed per execution. The figures below give you an idea of what generating an image normally costs. Most generations fall within this range. **Note:** Treat these figures as a planning estimate rather than a fixed rate. | Metric | Cost per image | In cents | | --- | --: | --: | | Median | $0.0388 | 3.88¢ | | Average | $0.0499 | 4.99¢ | Your actual cost per image will vary depending on how you configure the action. The main factors are: - **Model** – the AI model you select. - **Quality** – the quality level you set (Auto, High, Medium, or Low). - **Size** – the image size you generate at. - **Additional context** – applying a Design Kit or Brand Voice passes extra context to the model, which can shift the cost. --- ## **Frequently Asked Questions** **Q: How much does it cost to generate an image?** Generating an image normally costs between $0.0388 (3.88¢) and $0.0499 (4.99¢). Your actual cost depends on the model, quality level, and image size you select, and on whether you apply a Design Kit or Brand Voice. See the Pricing section above for more detail. **Q: Where is the generated image stored?** Every generated image is automatically saved to Media Storage and hosted at a publicly accessible URL. You can access it through the custom value picker in downstream actions or browse to it directly in Media Storage. **Q: Which model should I choose?** It depends on your use case. Models differ in visual style, photorealism, and how well they render text within images. If you’re unsure, run the same prompt through two models and compare the results before publishing the workflow. **Q: What does the Quality setting affect?** Quality controls the level of detail in the generated image. Auto (the default) lets the system choose an appropriate level for your prompt. High produces the most detailed output but takes longer to generate; Low is faster and lighter. Choose based on whether the image is customer-facing or an internal draft. **Q: Can I use dynamic data in the prompt?** Yes. The prompt field supports custom values, so you can insert contact fields, webhook payload data, or output from previous actions. This lets a single workflow generate a different image for every contact or every incoming request. **Q: What does Enhance Prompt do?** It uses AI to expand and refine your prompt, adding detail around style, composition, and lighting that you may not have specified. This typically produces noticeably better output. You can review and edit the enhanced prompt before saving the action. **Q: Do I have to use a template?** No. Templates are a starting point, not a requirement. You can write your own prompt from scratch, or apply a template and then edit the pre-filled prompt to match your exact requirement. **Q: How do I get a transparent background?** Open Additional Settings and set the Background option. The default is Auto; you can also select Opaque. For transparency to be preserved in the final file, choose PNG or WebP as the output format – JPEG does not support transparency. **Q: What are Design Kit and Brand Voice used for?** Both give the AI additional context so generated images align with your brand. Design Kit applies your visual style, while Brand Voice supplies your brand details. These options pull from the assets already configured in your account – if you haven’t set them up, configure them first and they’ll appear as selectable here. **Q: Can I send the generated image to an external system?** Yes. Because the image is hosted at a publicly accessible URL, you can pass the Image URL value to any downstream action – including outbound web-hooks to deliver it to an external platform. --- ### **Related Articles** - [Workflow Action - AI Extract Data](https://docs.ghlcustomercare.com/docs/workflows/workflow-ai-workflow-actions/workflow-action-ai-extract-data) - [Workflow Action - AI Translate](https://docs.ghlcustomercare.com/docs/workflows/workflow-ai-workflow-actions/workflow-action-ai-translate) - [Workflow Action - AI Agent](https://docs.ghlcustomercare.com/docs/workflows/workflow-ai-workflow-actions/workflow-action-ai-agent) - [Workflow Action – AI Analyze Image](https://docs.ghlcustomercare.com/docs/workflows/workflow-ai-workflow-actions/workflow-action-ai-analyze-image) --- Documentation for GHL Customer Care. Support: support@ghlcustomercare.com