Product presentation
A maker can test a restrained camera movement around a permitted product reference. Keep the product’s visible identity and geometry in the brief, then inspect the generated result for unwanted changes.
Image to video prompt.
Plan a camera move and a possible next moment from a still.
Find the first frame. Then decide what moves. Turn your reference into an editable shot plan.
YOUR CREATIVE WORKSPACEREFERENCE → PROMPT
01 / Your referenceNO SIGN-UP
Drop an image. Find its words.or click to choose a fileJPG, PNG, WebP · Up to 10 MB · Paste with Ctrl / ⌘ + V
The image host must allow browser access. If blocked, download and upload the file instead.
Up to 5 connected attempts per tool each UTC day. Remaining usage appears after a request.
Processed in memory. Uploads are never saved by this site. Privacy details
02 / Your promptAWAITING REFERENCE
→Aa
A picture is a starting point.
Your prompt will appear here, ready to edit, copy, and make your own.
A creative interpretation, never an exact reverse of an original prompt.
THREE CLEAR STEPSFrom a starting point
From a starting point
to your next creation.
- 01
Choose the opening frame
Upload an image that gives the shot a clear subject. Use a JPG, PNG or WebP up to 10 MB, with permission to share the reference.
- 02
Choose a writing target
Select Veo, Kling, Sora or a general video brief. These presets change the writing emphasis; they do not connect to a video generation service.
- 03
Review the motion plan
Read the camera movement, proposed subject action, duration and continuity instructions. Edit the plan before copying it into your chosen video tool.
AN ILLUSTRATIVE EXAMPLESee the brief.
See the brief.
Make the decisions.
This original writing example is not a live analysis of an uploaded reference.
INPUT
EXAMPLE
EXAMPLE
An illustrative still: a green ceramic cup on pale stone, lit softly from the left. TODO：用生图工作台生成。
THE EDITABLE OUTPUT
Creative motion proposal: begin with the cup in its original position. Use a slow camera push while a faint curl of steam rises. Keep the cup shape, table and light direction consistent. Suggested duration: five seconds, subject to the receiving tool’s controls. The movement is proposed, not observed in the still.
A brief you can work with.
01 / A USEFUL DETAIL
Make movement explicit
Separate what the camera does from what the subject does. A still image can anchor the scene, while the prompt proposes a possible next moment.
02 / A USEFUL DETAIL
Protect continuity
Name the shape, layout and lighting you want to keep. Constraints make the intent easier to review, although they cannot guarantee that a video model preserves every detail.
03 / A USEFUL DETAIL
Use a readable shot brief
Choose detailed prose, a compact description or JSON. The format remains an editable creative plan rather than verified vendor-specific parameter syntax.
WHEN IT HELPS
A place in your workflow.
An illustrated moment
An illustrator can propose one modest action or a shift in the environment. Start with a movement that suits the source scene, rather than asking every object and the camera to move at once.
A PRACTICAL FIELD GUIDEFewer assumptions.
Fewer assumptions.
A clearer direction.
A still does not contain observed motion
The reference gives you a starting arrangement, a subject and a visual atmosphere. It does not reveal what happened before or after the captured moment. Every motion instruction generated here is therefore a creative proposal. Read it as a possible shot, not a factual account of action hidden in the image. If the proposed movement does not fit your concept, replace it directly in the output. A quiet frame may work with a small shift in light or background activity rather than a dramatic subject action.
Give the camera one clear job
A camera instruction becomes easier to evaluate when it describes a single movement. Consider whether the viewer should approach the subject, travel alongside it or stay in a fixed position. Then name what remains stable in the frame. Avoid piling several conflicting moves into a short shot merely because they sound cinematic. This is an editorial planning suggestion, not a rule that a video service must follow. The generated video can still interpret distance, speed and framing differently, so compare the result against the intention you wrote.
Keep subject action separate
Camera movement and subject movement can create very different effects. A cup may stay still while the camera approaches it; a person may turn while the camera remains locked. Describe those roles separately and keep the action plausible for the scene you want to create. The tool can suggest a modest action, but it cannot establish a person’s intention or identify an unseen event from a photograph. Remove any assumption that does not belong in your own creative direction, especially when the reference depicts a real person.
Duration is a proposal, not a setting guarantee
The sample brief uses a proposed five-second beat to make the idea concrete. That number is not a promise that every listed video model accepts the same duration, format or control. Check the current options in your chosen generation application before using the plan. A short movement may need less time than a sequence of distinct actions. If the idea requires multiple shots, plan them separately rather than expecting a single still-to-video prompt to communicate a complete edit. This tool drafts text and does not render or assemble a video.
Continuity needs a deliberate review
Look beyond the central action when you evaluate a video produced elsewhere. Check whether the background layout, product shape, lighting and any important lettering remained suitable. A motion brief can explicitly ask to preserve those details, but the instruction is not an assurance of pixel-level consistency. For a new attempt, simplify the action and name the most important constraints again. Keep your own comparison copies if the material is appropriate to save. Aizvu does not maintain a history of uploaded references or generated shot plans.
Choose the format for your next step
Detailed output gives camera motion, subject action and continuity room to read together. Short output can help when you want one compact shot instruction. JSON separates those fields and a proposed duration for easier inspection in your own workflow. These structures are Aizvu writing aids, not official request formats for Veo, Kling or Sora. The target menu selects an editorial preset only. In local example mode the reference has not been analyzed; the labelled sample lets you test editing and copying without calling a connected vision model.
GOOD TO KNOW
Before you create.
01Does this generate a video?+
No. Aizvu returns a text or JSON shot plan. Video generation happens separately in the application you choose.
02Can a still reveal its next movement?+
No. The opening frame is observed, while camera movement, subject action and duration are creative proposals to review and edit.
03Do the presets guarantee vendor syntax?+
No. Veo, Kling, Sora and General video are writing targets. Confirm supported durations and controls in the receiving service.
04What should remain unchanged?+
Name the subject shape, scene layout, lighting and any lettering you want to preserve. Inspect the generated result rather than assuming those constraints are guaranteed.
05Can I use JSON?+
Yes. JSON can separate scene, camera movement, subject movement, continuity and suggested duration. It is a site-defined creative schema.
06What happens to the reference?+
The application processes it in memory. Connected mode sends it to the configured vision provider, whose policies apply; local examples do not analyze it.