> For the complete documentation index, see [llms.txt](https://docs.agenticflow.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.agenticflow.ai/use-cases/agent/marketing/create-ugc-image-feedback-or-clothing.md).

# Create AI-Assisted UGC-Style Image (Nano Banana PRO)

[Agent link template](https://agenticflow.ai/app/marketplace/items/01KCKH2V31XQXVJAABCF86FP7K)

### **👉 Goal**

Quickly generate a large volume of UGC image feedback for clothing without the extra cost of hiring models or professional photo studios.

***

### **⚙️ Overall Process**

<br>

1. (Start)

↓

2. User uploads images

↓

3. Validate input

↓

4. \[Decision]

Are model & product images provided?├─ No → Ask user to upload missing images → (Back to Upload)└─ Yes↓

5. Run UGC Image Feedback workflow

↓

6. Output UGC image + image URL

↓

7. \[Decision]

Edit image?├─ Yes → Run Edit Image workflow → Output edited image + URL → (End)└─ No → (End)<br>

***

### **🛠️ Required Tools**

* **2 workflows**
  * One workflow to edit images for generating UGC image feedback
  * One workflow to edit the final images if the results are not satisfactory
* **1 agent**: designed to interact with users and allow them to process multiple images at the same time.

***

### **📝 HOW TO USE**

\
\--> **Example inputs:** Model Image and Product Image [link](https://drive.google.com/drive/folders/1sDClLNaKFw5V9AubTHl0cGH92OB-gUzH?usp=sharing)\
\--> **Input Requirements:**

<figure><img src="/files/piSysQYEYqruhKv4yKLR" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/6nmogJ4KG0jafoyKrofa" alt=""><figcaption></figcaption></figure>

#### Step 1: Say hi & upload your images

* You can start by saying **“Hi”** or sending a message so the agent can introduce itself and explain what inputs are required.
* Then, upload **both required images**:
  * **Model image**
  * **Product image**
* There are 3 scenarios you can use:
  * (1) Upload 1 product image and 1 model image → no additional prompt is required.
  * (2) Upload 1 product image and multiple model images → add the following prompt:

*“The first image is the product image, and the other two images are model images. Generate two images of the two models wearing the product image.”*

* (3) Upload 1 model image and multiple product images → add the following prompt:

*“The first image is the model image, and the other three images are product images. Generate three images of the model wearing each of the three product images.”*

#### Step 2: Wait for validation

* The agent will automatically check your uploads.
* If any image is missing, the agent will ask you to upload it.

#### Step 3: Generate UGC images

* Once both images are provided, the agent will automatically generate **UGC image feedback**.
* Simply wait while the images are being created.

\
Example:

<figure><img src="/files/MytFIpw6NwX49iUzmYTk" alt=""><figcaption></figcaption></figure>

#### Step 4: View and use the results

* You will receive:
  * The generated UGC images
  * Public image URLs for each image
* You can:
  * Preview the images
  * Download them
  * Use them for ads, social media, or product pages

#### Step 5 (Optional): Edit images

* If you want to edit an image:
  * Send an **edit prompt** describing the changes
  * Upload the **image you want to edit**
* The agent will process the request and return the edited image with a new URL.

\
Example: Create three different standing poses for the image

<figure><img src="/files/8o1oan2GenAUwSEDj7lD" alt=""><figcaption></figcaption></figure>

#### Step 6: Finish or generate more

* You can:
  * Generate more UGC images
  * Continue editing
  * Or end the session when you’re satisfied