Showcases

Fashion Outfit-Change Triple Take: Fast-Cut Transitions with Reference-Image Consistency

Using reference-image-to-video generation, three looks of the same model are compressed into a single 9:16 vertical short film: the camera completes the outfit changes at three beat points, connected by push-pull and occlusion transitions, while keeping the character's face, hairstyle, and accessories consistent across shots throughout. The three look reference images are bound in the order Image1/Image2/Image3 and called out by name node by node in the prompt, making this suitable for clothing brand lookbooks, social media ad assets, and short-form displays for new product launches. The assets are generated by an image-to-image pipeline, and the final film is output in one pass by Vidu Q3 reference-image-to-video, making it suitable for creating this kind of multi-reference-consistency fashion short film with that model family.

Style Fashion Film · Quick Cut · Product Catalog

Model vidu-q3-ad

Reference inputs

reference_image_urls
reference_image_urls
reference_image_urls

Try-it is unavailable: this model's playground configuration isn't ready yet.

Prompt

Try this model

Vertical 9:16 fashion lookbook video, a single continuous take completing three outfit changes in succession. It opens on a full-body medium shot of the model in the first look, with soft studio key light coming from the left side of the lens and a subtle rim light; a quick push-in to the chest follows, then a hand sweeps across the lens as a wipe transition. Cut to the second look at a slightly low angle, the camera orbits a quarter turn clockwise while the model turns in the opposite direction; a fast whip pan to the wall completes the second transition. For the final look, the camera quickly pulls back to a wide full-body composition, and the model stands in a confident pose with a small step forward as the fabric and hair gradually settle. Across all three segments, the face, hairstyle, and body proportions remain consistent, with a clean seamless background, restrained editorial-style color grading, clear fabric texture, stable motion, and no distortion of facial features or clothing logos; total duration 12 seconds, with an even rhythm that stays on beat.

Copy the full prompt and adapt it for your own generation.