Create videos from text or a starting image with Google Veo 3.1. Describe the action, camera movement and optional audio.
Google’s video model lets you describe a moment as a moving scene. On Maxsa, start from words or one image, then choose the framing and sound for your clip.
Start with a subject and an action: a cyclist crossing a bridge, steam rising from a cup, or a character opening a door. Add the camera angle and lighting to make your intention clearer. A short, focused scene is easier to refine than an entire story squeezed into one generation.
Upload an illustration, photograph or product image as the starting point. Describe what changes over time rather than repeating everything already visible. Try a gentle push-in, moving fabric or a shifting reflection. Use a sharp image with the subject clearly framed.
Enable audio when the scene needs ambience, effects or dialogue. Name the sound and its source: rain against a window, footsteps on gravel, or a single spoken line. Keep speech brief, and listen to the result before publishing.
Ready-to-use directions for the scene, camera, lighting and sound. Copy the full prompt or send it straight to the creator, then make it your own.
Suggested: 8 seconds · Audio on
A realistic close-up of a clear, unbranded perfume bottle on dark, slightly textured stone. Place the bottle in the right third of the frame, leaving soft negative space on the left. A thin ribbon of mist moves slowly behind it while the bottle stays still.
Use one continuous, slow camera orbit from front-left toward the front of the bottle. Keep the cap and glass edges sharp, with a shallow depth of field and a softly blurred background. Warm side lighting creates a narrow highlight on the glass; a cooler fill light separates the bottle from the stone.
Keep the motion restrained, with no scene cuts or sudden zooms. Audio: a faint breeze and a subtle glass chime near the end. No speech, music, titles or added logos.
Suggested: 8 seconds · Audio on
A hand-painted anime scene at a small rural railway station at sunset. An adult traveler in a moss-green coat stands beside a wooden bench, holding a worn canvas bag. Keep the traveler slightly off-center, with the empty railway track visible behind them.
Begin with a medium shot at eye level. The camera slowly pushes closer as a light breeze lifts the traveler’s scarf. They turn their head gently toward a distant train light, then hold that pose. Keep the movement within one uninterrupted shot rather than cutting to the train.
Use warm amber sunlight, soft shadows and a quiet, reflective mood. Preserve the coat, face and bag throughout the shot. Audio: rustling leaves, a distant rail hum and a faint station bell. No dialogue, subtitles or on-screen lettering.
Suggested: 8 seconds · Audio on
A realistic early-morning street scene outside a small neighborhood bakery after light rain. Wet cobblestones reflect the warm light from the shop windows. Place a few empty café chairs beside the doorway and keep the street calm, without a moving crowd.
Use a low, wide view and a slow forward tracking movement toward the bakery. A shopkeeper opens the door partway and pauses, while a trace of steam rises from a cup on the nearest outdoor table. Keep the movement gentle and the framing steady, with no abrupt transitions.
Balance cool morning daylight with warm light inside the bakery. Show natural reflections and detailed stone textures without exaggerated gloss. Audio: a soft door bell, distant birds and a brief scrape of a chair. No narration, music, subtitles or added text.
Think like someone describing a single shot. Start with what matters most, then add only the details that change the result. When testing variations, change one instruction at a time so you can judge its effect.
Build your scene ↑“A traveler turns toward an arriving train” gives the scene something specific to do.
Choose a close-up, medium shot or wide view. Request one camera move, such as a slow pan, instead of conflicting movements.
Specify soft daylight, neon reflections or illustrated textures. For image input, focus on preserving the look while adding motion.
Add ambience or a short line of dialogue if audio is enabled. Leave enough time for the action to read clearly.
Choose your output before generating. Available combinations depend on the selected version.
| Starting point | A text prompt, or one JPG, PNG or WebP image up to 10 MB |
|---|---|
| Video length | 4, 6 or 8 seconds at 720p |
| Higher resolution | 1080p and 4K use an 8-second clip |
| Framing | 16:9 landscape or 9:16 portrait |
| Sound | Optional audio, controlled in the creator |
This workflow uses one starting image. Multiple reference images, a separate end frame and video extension are not available here.
Compare the version and settings before committing credits. Use the same prompt across versions to decide which result fits your project.
| Version | Output on Maxsa | A useful starting point |
|---|---|---|
| Veo 3.1 | 720p, 1080p or 4K · optional audio | Explore the standard model with your finished shot direction. |
| Veo 3.1 Fast ↗ | 720p, 1080p or 4K · optional audio | Try another version with the same resolution options and compare its credit quote. |
| Veo 3.1 Lite ↗ | 720p or 1080p · optional audio | Explore ideas when you do not need 4K output. |
All three support text or one starting image. The creator shows the quote for your exact settings; processing time and results can vary.
Write your scene or upload a starting frame. Pick landscape for a wide composition or portrait for a vertical edit. Check that your subject has room to move.
Choose quality, length and audio, then review the credit quote. After generation, watch the whole clip for motion, visual continuity and sound. Refine one detail if it needs another pass.
Download the clip you want to keep. Use the saved prompt to explore a variation, or combine downloaded shots in your preferred video editor for a longer sequence.
You can request an anime look in a text prompt or start with your own illustration. Describe the motion you want, such as a head turn or moving hair. A starting image guides the composition, but exact character details may change during generation.
Select 9:16 in the Frame control before generating. For image-to-video, use a portrait image when possible and keep important details away from the edges.
Enable Audio and describe the sounds in your prompt. For speech, specify who is speaking and keep the line short. Check pronunciation, timing and background sound in the generated clip.
The Veo 3.1 configuration on Maxsa requires eight seconds for 1080p and 4K. At 720p you can choose four, six or eight seconds.
The quote depends on the model version, resolution, duration and audio setting. Review the displayed cost before confirming. Changing these settings can change the quote.
This creator makes individual short clips. Plan a longer sequence as separate shots, download the selected clips and assemble them in a video editor. Direct video extension is not offered in this form.
Use Download video on the completed result to keep your own copy. Download important work before clearing browser storage or switching devices; do not rely on a browser preview as your only copy.
Read the job status before trying again. If it is still processing, wait rather than submitting a duplicate. If it fails, check the image and prompt, then retry or contact support with the job details.
Start with a moment. Give it movement.
