we live in a CRAZY ERA from now you can generate 100 videos a day in one

提示词

we live in a CRAZY ERA
from now you can generate 100 videos a day in one click. with GENJUTSU on DAAS
here's the exact prompt i used for this one:

Create a photorealistic video using the uploaded image as the identity reference and the uploaded video as the motion reference.
SUBJECT
The subject is an adult woman aged 25 or older. Use the woman shown in the uploaded image as the visual identity reference. Preserve her facial features, face shape, eye color, nose shape, lip shape, skin tone, and natural hairstyle.
HAIRSTYLE AND NAILS
Her hair is straight and tied into a ponytail. Two blonde strands frame the front of her face. Her nails have a classic French manicure with a pale pink base and white tips.
ACTION
Reproduce the visible movements from the uploaded video in the same order and at the same pace. Match the head movements, hand gestures, facial expressions, body position, and direction of gaze. Do not add movements that are not present in the reference video.
CAMERA
Match the reference video's camera angle, framing, subject position, and duration. Keep the camera movement consistent with the original video.
VISUAL CONSISTENCY
Keep the same adult woman recognizable throughout the entire video. Maintain consistent facial features, hairstyle, clothing, body proportions, and nail design in every frame.
IMAGE QUALITY
Use realistic skin texture, natural lighting, accurate anatomy, anatomically correct hands, five fingers on each hand, realistic hair movement, and smooth transitions between frames.
CLOTHING AND SCENE
Keep the clothing and setting appropriate for a general audience. Preserve the original outfit when it is suitable for general audiences. Do not add revealing clothing, nudity, sexual content, or suggestive gestures.
OUTPUT REQUIREMENTS
Produce one continuous, photorealistic video. Follow the reference video's sequence of actions without adding unrelated scenes, extra people, text, logos, or watermarks. Prioritize identity consistency, accurate motion reproduction, and realistic visual quality.