Creating ad videos used to require a model, a shoot, and post-production. XBRUSH AI Studio Talk To You cuts that down. Choose an AI model from the marketplace, composite your product image, set up the voice, and the lip-sync ad video is ready.
Step 1: Choose a Model
Browse the persona list and choose an AI model for your ad. Models come in a range of styles and moods — click one to start production.
Step 2: Choose a Starting Image
Select the starting image for your chosen model. Pick from the model's available poses and backgrounds to match the vibe of your ad.
Step 3: Composite the Product
Upload your product image to composite it with the model image. Background removal and sizing are handled automatically.
Step 4: Generate the Voice
Enter a script and generate the voice. Use XBRUSH's auto script generation or write your own.
Step 5: Generate the Video
Once everything is set, kick off video generation. Choose orientation (portrait/landscape) and size, and the AI produces the final lip-sync video.
Finished Ad Video
Frequently Asked Questions
What product images can I use?
Upload JPG or PNG product images. Images with a clean background where the product is clearly visible produce the most natural composites.
Do I have to write the script myself?
You can write it yourself or use XBRUSH's AI script generation. Enter your product name and key features and the AI suggests an ad script.
Can I use the generated lip-sync video directly in SNS ads?
Yes. Upload the generated video directly as a creative to Instagram, Facebook, YouTube, Kakao, and other major ad platforms.