Give a product photo, character sketch or scene idea its next movement. Use one image or start with words, shape a short shot, and choose whether it needs generated sound.
PixVerse V6 Max brings text-to-video and single-image animation into FireRed Image Edit. It is useful when you need a moving draft for a product post, a storyboard beat or a visual experiment. Choose a focused action, generate a short version and inspect it before taking the clip into an editor. An image sets the framing; a written brief sets the intended movement.
Prepare the source, control the output and inspect the full result.
Decide what the viewer should notice: a bottle turning on a table, fabric moving in a breeze or a character looking toward the camera. Put that action beside the subject and camera direction in your brief. Text-to-video can begin without an image. Keep lettering, exact logos and final captions for an editing step, where you can control them precisely.
Use one sharp JPG, PNG or WebP, no larger than 20 MB and with both sides at most 10000 pixels. Upload it to FireRed or choose a compatible library image. In image-to-video, the source crop determines the output shape. Describe the moving subject and the areas that should remain still; this mode does not accept an ending frame.
Select a whole-second duration from 1 to 15 seconds, with 360p, 540p, 720p or 1080p output. For text-to-video, choose 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 or 21:9. For an image-led clip, crop the image first because its shape replaces the ratio setting. This workspace does not offer Max output at 4K.
After signing in, select the input mode and enter a prompt of 1–5000 characters. Switch generated audio on only when the scene needs it; the model does not accept an uploaded soundtrack here. An optional integer seed can help organize comparisons. Confirm the settings, submit once and follow the task status. Max does not provide video extension, first/last-frame transitions, video references or multi-clip editing.
At five seconds, 720p costs 53 credits with audio off and 72 with audio on. The same length at 1080p costs 106 or 135 credits. Longer duration, higher resolution and sound affect the estimate. Read the displayed total before submitting. A short first version lets you check the direction before spending credits on a longer take.
Review the entire timeline for faces, hands, product geometry, background movement and unexpected text. Listen to generated sound when enabled. Download with the result controls and open the saved file before adding captions, music or other shots in your editor. Output accuracy and waiting time vary. Use source material you have permission to process and review the applicable terms before publishing.
Supplied demonstration video; the cover is an original AI illustration. Neither is a generation test performed on this site.
Create Short Videos with PixVerse V6 Max FAQ
No. Write a scene brief for text-to-video, or upload one image for image-to-video. Both modes need a description of the action. For a product post, a prepared photo helps set the appearance; a text brief is enough for an early scene concept.
Prepare a single JPG, PNG or WebP up to 20 MB, with neither side exceeding 10000 pixels. Crop it to the intended frame before uploading. A clear subject and an explicit motion description make the result easier to assess.
Yes. The available lengths are whole seconds from 1 to 15, and the resolutions are 360p, 540p, 720p and 1080p. The initial setting is five seconds at 720p. Max has no 4K output option in this workspace.
For text-to-video, select 9:16; 21:9 and six other ratios are also available. For image-to-video, upload a photo already cropped to the desired shape. Its dimensions determine the frame, so there is no separate ratio setting.
Generated sound is optional and changes the estimate. This Max integration does not accept an uploaded audio track. Add a chosen soundtrack in your editor if you need exact music, speech or timing; generated audio does not guarantee those details.
At 720p the estimate is 53 credits without sound or 72 with sound. At 1080p it is 106 or 135 credits respectively. Check the on-screen estimate for your selected duration, resolution and audio setting before generating.
Max here starts from text or one image. It does not accept an ending frame, a video reference, video extension or multi-clip instructions. Use the linked model pages to compare other available workflows before preparing those inputs.
The supplied video is a model demonstration, while the FireRed cover is original AI artwork. They are not a record of a generation test on this site and do not guarantee your result. Inspect your own full clip and downloaded file before use.
Start with a clear photo or a scene brief. Choose your duration and sound settings, check the credits and create a draft you can review.
10,000+ users
