Editing Images — Customizing
The Image Gen tool lets you edit images with AI-powered operations, including maintaining character consistency with AI Actors, modifying character appearance or clothing, adjusting lighting, and refining rendering styles or camera angles.
Required Elements
- Reference (v1.01): Up to 8–14 total references (AI Actors and images combined), depending on the selected AI model. Maximum 4 AI Actors. Supported image formats: PNG, JPG, JPEG, and WebP.
- Prompt: Enter custom prompts manually, or apply preset prompts if you’re unsure where to start.
AI Settings
Select the Image Gen
tool from the left AI Toolbar and complete the tasks in each section under the Edit tab.
You can collapse or expand a section by clicking its caption.
Refer to AI Model Selection for Image Generation to choose a model from the Model drop-down list.
Available options include Nano Banana Pro, Flux 2 Max, and Gpt Image 2.

The total number of references depends on the AI model (see table below). AI Actors and images share a combined limit, such as 4 AI Actors + 10 images or 2 AI Actors + 12 images for Nano Banana Pro.
| AI Model | AI Actor | Image | Total References |
Nano Banana Pro | Up to 4 | Up to 14 | Up to 14 |
Flux 2 Max | Up to 8 | Up to 8 | |
Gpt Image 2 | Up to 10 | Up to 10 |
- Click the Custom button in the Operation section.

- Click the Reference 1 slot, then select AI Actor to ensure consistent character appearance in the generated images.

- Choose one or more actors in the AI Actor Manager, then click Select at the bottom.

- The selected AI Actors will be placed in the Reference slots, each with preset appearance prompts.

- Repeat the process by clicking the Reference slot and selecting Image to add more references.
Upload an image (.png, .jpg, .jpeg, or .webp) for the actor’s outfit, or drag and drop it from Windows File Explorer.

- Hover over a Reference thumbnail to preview the input.
To update it, drag and drop a new item to replace it, or click the Trash button to remove and add a new reference.

Each reference is represented by a label tag in the Prompt field for quick editing and reference assignment.
Click the Reset Prompt button to clear the prompt field and start over if needed.

- Move tags anywhere within the prompt by cutting and pasting them.
- Click Copy on a reference thumbnail to add its tag to the prompt, or type @ to insert a reference tag from the context menu.


|
|
Change Farah 's cloth and Ariana's cloth to the same dress shown in Image 1. Preserve the dress design, color, fabric, and overall style from Image 1.
Change Aaron's cloth and Tate's cloth to the same suit shown in Image 2. Preserve the suit design, color, fabric, and overall style from Image 2.
The scene should feel lively and elegant, with the four characters enjoying their walk together in a joyful mood".
Set the image ratio and resolution using the Ratio and Resolution drop-down lists in the Render section.

Supported options may vary slightly by AI model, as shown below.

The additional Randomize or Fixed Seed option is available when using the Flux 2 Max model, allowing you to control or vary the generation seed for AI rendering results.

Each submitted task is charged using your available AI, Bonus, or DA Points.
Click the account icon in the bottom-left corner of AI Studio to view your current point balance.
Points are deducted in the following order: AI Points → Bonus Points → DA Points.

To obtain additional credits, subscribe to an AI Service Plan for more AI Points, or purchase DA Points to top up your account.
Ensure both a reference and a prompt are provided to enable the GENERATE button.
Check the task price displayed above the button before generating.

Track progress on the AI Render View or via the new entry in History on the right.
When the submission completes successfully, the AI-generated image will appear.

Next, use the Video or Talking Actor options in the Quick Access Menu at the top of the AI Render View to load the generated image as a reference for creating a video or talking animation.


