Vidu AI Video Generator: Text & Image to Video with Sound
Use Vidu AI on OCMaker AI to turn text or an image into a 4 to 16-second video with sound, up to 1080p, with Vidu Q3 Pro and the newer Vidu Q4.
Vidu is the video model family from ShengShu Technology, popular for anime and cinematic clips. On OCMaker AI, Vidu Q3 Pro turns a prompt or an image into a 4 to 12-second clip with sound, and Vidu Q4 animates an image for up to 16 seconds.
Example clips created on OCMaker AI.
1girl, a beautiful forest elf with long flowing silver hair and soft emerald-green eyes stands gracefully among ancient trees. Her delicate features and calm expression give her an ethereal presence. She wears an elegant flowing dress made of layered leaves and silk-like fabric, gently moving with the forest breeze. The environment is a magical woodland filled with towering trees, glowing fireflies, and rays of sunlight filtering through the leaves. Moss-covered stones and small flowers surround her feet, creating a tranquil natural atmosphere. The camera perspective is eye level with slight cinematic depth of field, focusing on her serene face while the forest softly blurs into the background. Ultra detailed fantasy style, 8k resolution, soft natural lighting, magical particles floating in the air, cinematic fantasy atmosphere.
1animal, a powerful fluffy snow wolf standing on a frozen mountain ridge. Its thick white fur moves in the cold wind as snow drifts across the landscape. The wolf's piercing eyes stare forward with quiet dominance. The environment is a vast snowy mountain range under a dramatic cloudy sky. Snow particles move through the air, and distant peaks stretch across the horizon. The camera angle is low and cinematic, emphasizing the wolf's majestic posture. Ultra detailed fur, dramatic cold lighting, cinematic wildlife film style, 8k quality.
1girl, a beautiful young woman with long dark hair and bright expressive eyes stands on a quiet beach during golden sunset. Her hair moves gently in the ocean breeze and she wears a simple flowing white dress that catches the warm sunlight. The beach environment features calm ocean waves, reflective wet sand, distant seagulls, and glowing clouds painted by the setting sun. The water reflects warm orange and pink tones. The camera uses a cinematic wide shot with slow motion movement, capturing the woman walking slightly toward the shoreline. Ultra realistic detail, 8k film quality, warm golden hour lighting, soft shadows and natural atmosphere.
Example clips created on OCMaker AI. Each description includes a prompt idea you can try with Vidu.
0104
Start from text alone with Vidu Q3 Pro. Name the character, one clear action and the camera move. Prompt idea: an anime swordswoman on a windy cliff draws her blade and slices through a stream of falling cherry blossom petals, then sheathes it and glances at the camera.
0204
Add an image and it becomes the first frame; describe what happens next. Vidu Q4 animates images for up to 16 seconds. Prompt idea: the barista finishes the pour, tilts the cup to show the latte art and slides it toward the camera with a smile.
0304
Vidu clips come with sound made together with the picture, so write the sounds you want to hear. Prompt idea: a street cook fans glowing charcoal and brushes glaze on sizzling skewers under an awning while rain patters on a wet street at night.
0404
Stylized 3D characters work well too; give them small, funny actions. Prompt idea: a little teapot-shaped clay robot waters a seedling, does a happy wobble when a new leaf uncurls, and freezes when a ladybug lands on its head.
Vidu Q3 Pro for text or image to video; Vidu Q4, the newer model, to animate an image.
Start from a prompt with Vidu Q3 Pro, or add an image to use as the first frame.
Clips come with sound generated together with the video.
Vidu Q3 Pro makes 4, 8 or 12-second clips; Vidu Q4 goes up to 16 seconds.
Choose 540p, 720p or 1080p for each clip.
From 8 credits for a 4-second Vidu Q4 clip at 540p.
The generator above opens on Vidu Q3 Pro. Switch to Vidu Q4 when you start from an image and want the newest Vidu model or a 16-second clip.
Describe the action, the camera move, the mood and the sounds. Text-to-video clips can be portrait 9:16 or landscape 16:9.
Pick the length and 540p, 720p or 1080p; the credit cost updates as you choose. Download the clip when it is ready.
Vidu is a family of AI video generation models from ShengShu Technology. On OCMaker AI you can use two of them: Vidu Q3 Pro, for text or image to video, and Vidu Q4, which animates an image. Both add sound to the clip.
Vidu is available to members. Vidu Q3 Pro costs 10, 20 or 30 credits at 540p, 12, 24 or 36 at 720p, and 14, 28 or 42 at 1080p for 4, 8 or 12 seconds. Vidu Q4 costs from 8 credits (540p, 4 seconds) to 78 credits (1080p, 16 seconds).
Yes. Both Vidu models generate sound together with the picture. Describe the sounds you want, such as rain, footsteps or sizzling food, in your prompt.
Vidu models are for members. MiniMax H3 works without a membership and also makes videos with native sound, from text or an image.
Text-to-video clips can be portrait 9:16 or landscape 16:9. When you start from an image, the video keeps the image's shape.
Text or image to video with sound, 4 to 16 seconds, up to 1080p.
