Keep the picture as your starting point. Use Image to Video to explore what the subject or camera does next.
Image to Video starts from a picture whose look you already want to use. The image establishes initial visual information, your prompt describes movement, and the model generates the continuation. Explore a gesture or camera move, then review the clip. Recreating exact existing choreography needs a separate video-reference workflow.
Choose a movement that makes sense for the picture you already have.
STEP 1
Upload a clear image with the subject and framing you want to begin from. Check the preview and decide what should move.
STEP 2
Write a focused motion prompt, then choose the supported output settings. Read the credit estimate for the full request before continuing.
STEP 3
Sign in and submit when ready. Watch the Image to Video result from beginning to end and compare it with the original before downloading.
Explore the action and camera direction that best support your existing image.
Give a product picture a reveal or a gentle change in viewpoint with Image to Video. Describe what should move and which subject matters most. Generated frames can alter labels, shapes, and reflections, so compare the result with the original. The example suggests a direction rather than guaranteeing precise reproduction.
Use Image to Video for a slow approach, drifting viewpoint, or subtle environmental movement in a scene you pictured. The still supplies its initial atmosphere. A large camera turn reveals unseen areas that the model must imagine, so choose how far to go and inspect what appears beyond the original frame.
Let an illustration gain a moving viewpoint while keeping a clear focal point. Image to Video interprets shapes and materials that may be ambiguous in a still. Choose one action, then check whether the moving result preserves the qualities you value in the artwork before including it in a larger project.
A character image can begin a turn, expression, or small gesture. Image to Video infers motion from one frame, so choose an action that fits the visible body. A face-only crop leaves a full-body dance largely unspecified. For a particular performance, use the homepage workspace with a separate motion reference.
This entrance keeps a starting image close to the motion prompt.
Try a small motion that adds life without asking the model to reveal a completely different scene. Image to Video can help explore expressions, environmental movement, or a quiet camera approach. Inspect the transition from the starting frame to the moving result.
Use the image as a visual anchor for a short moving asset in a pitch or social edit. Choose a supported frame and duration that suit the destination. Precise text overlays, cuts, and final sound assembly can be added after downloading.
Keep the same image while changing one clear action in a later request. That makes it easier to compare a camera approach with a subject movement. Each submitted Image to Video version has its own cost, so decide what you want the comparison to answer.
Your starting picture and motion brief work together with the chosen model.
Upload the still in Image to video mode. The preview lets you check that the correct image is selected before you describe the next moment or submit.
Describe the main action and viewpoint. Keep conflicting camera directions out of the same short request. Image to Video interprets your brief rather than exposing a frame-by-frame animation timeline.
Choose from the available video models. Switching the model can change the supported duration, resolution, aspect ratio, and sound options, so review the current controls after a change.
A sound setting appears where the selected model supports it. Check whether it is enabled and whether the estimate changes before submitting; not every image-animation model offers generated audio.
The composer shows the credits for the selected request. Changing an image or editing the prompt only changes the draft. Submission is the point at which you start another generation.
Review and download a completed clip from My creations. Use available video history to revisit saved work, then add final cuts or graphics in your own editor if the larger project needs them.
The estimate beside Generate reflects your current Image to Video request. Preparing a draft does not spend generation credits; a submitted variation is a new request.
For your first ideas.
$100.0 charged yearly
2,400 credits/year
Up to 400 images
Up to 240 videos
For a steady creative flow.
$360.0 charged yearly
21,600 credits/year
Up to 3,600 images
Up to 2,160 videos
For more creations, more often.
$599.0 charged yearly
48,000 credits/year
Up to 8,000 images
Up to 4,800 videos
Try before you subscribe
Prices in USD; taxes and total shown at checkout. Subscriptions renew automatically; cancel in Billing settings. Subscription credits expire each period; one-time credits never expire. Refund requests: within 72 hours. Eligible refunds deduct used purchased credits and, where permitted, actual non-returned processing fees. Processing fees are capped at 6% of the original purchase amount, excluding separately charged taxes. Terms · Refund Policy.
Starting pictures, motion, credits, and Image to Video results.
Image to Video uses it as the visual starting point for the clip. Your words describe movement beyond that frame. The model generates the continuation, so later details can change rather than remaining an exact copy of the still.
No separate performance clip is required for this starting-image workflow. If your goal is to reproduce a specific gesture or dance from an existing video, use the main Genjutsu AI workspace with a video reference instead.
For Image to Video, use a clear image whose framing shows the parts of the subject involved in the motion. A visible face and upper body can suit a small gesture; a full-body action needs more visual information. Avoid heavy blur or major obstructions.
Image to Video can use an authorized illustration as the starting picture. The selected model interprets its shapes and style as they move. Review whether the output keeps the qualities you need, especially when the original uses unusual anatomy or ambiguous perspective.
The Image to Video picker offers the models currently published for this workflow. Supported modes and settings follow your selection. Review the displayed controls before submitting, particularly after changing models in an existing draft.
Image to Video can interpret a camera movement in the prompt. An orbit asks the model to imagine parts of the scene outside the initial view, so new details may appear. Inspect the completed movement rather than assuming it will follow an exact path.
Use the Image to Video duration choices displayed by the selected model. Each model supports its own combination of length, resolution, frame, and sound. The current settings and estimate describe the request you will submit.
Image to Video does not guarantee exact preservation. New frames can change lettering, facial details, hands, or accessories. Review the result closely when those details affect your use, and choose a more focused motion if your original request revealed too much unseen information.
Check the Image to Video estimate after selecting the model, length, resolution, and any supported sound option. You need sign-in and enough credits to generate. Preparing the picture or revising the prompt does not automatically submit another request.
Download a completed Image to Video clip after reviewing it. Your rights to the starting image, any recognizable people or protected material, and the intended destination still apply. The tool does not provide a blanket license for every reference or final use.
