Text to Video · MiniMax H3 LoRA · original 5.17s clip
Fashion portrait from text
Watch an original XVideo AI Text to Video sample with a head turn and lapel movement. See the prompt, settings and observed limitations.
XVideo AI sample ·
What we saw. The subject turns from a side profile toward the camera while her hands move at the blazer lapels. The green jacket and car setting remain recognizable through the shot.
Try next. Test one gesture first. Keeping the pose simple makes the head turn and lapel movement easier to judge before adding a walk or a larger camera move.
Sample settings and limits
Input
Original text brief
Model
MiniMax H3 LoRA
Requested
5s · 768p
Original file
768 × 1344 · 24 fps · 5.17s
Hand positions change during the clip. Check fine finger and fabric details in the original video before using a frame; this sample does not establish consistent anatomy across generations.
These are observations from one clip. The suggested next brief has not been render-tested.
A fictional East Asian adult woman aged 31 wearing a lime-green tailored blazer over an opaque white crewneck T-shirt and black tailored trousers, standing beside a dark parked car in a modern architectural showroom. Eye-level medium fashion portrait centered on her face and jacket, realistic adult proportions, calm confident expression, soft cinematic side lighting and charcoal background. She gently adjusts the jacket lapel and turns her face toward the camera, a slow restrained camera push-in. Preserve clothing and facial identity. Natural subtle movement, quiet ambience, no speech, no text or logos.
Copying a prompt does not restore every setting. Select the model, duration and resolution separately in the studio. The suggested next brief in the notes has not been render-tested.