Start from words
A written description is enough. Name the subject, the action and the camera, and Seedance 2.5 builds the shot - lighting, motion and lens behaviour included. Best when nothing exists yet and you are still finding the idea.
Example
An example of what this page produces.
AI Video Maker
Create product, social, and campaign video shots
Create product, social, and campaign video shots
Describe the scene, the character action, and the camera move. e.g. “slow dolly-in on a lone figure crossing a neon-lit street in the rain”.
Model
New in 2.5: generate up to 30 seconds, guide motion with as many as 30 images, or start from audio alone.
4s30s
Free credits are for a quick preview, not the final video. Use a short duration and lower resolution to check the subject, motion, and prompt. A fuller, more compelling final shot often needs a longer duration and higher supported resolution—use paid credits when your scene needs those settings.
Audio
With audio
Synchronized sound, voice and music
Maximum credits reserved:25
Your generated video appears here. Describe a shot and hit Generate.
My creationsDownload
Popular AI video generator workflows
Choose a focused workflow for transitions, extending a clip, or guiding a shot with start and end frames.
- AI Video TransitionUpload two images, describe the connecting motion, and generate a new AI video transition between them. Review the in-between frames for drift or artifacts before editing.Open workflow
- Start & End Frame AI Video GeneratorUpload a required first frame and last frame, describe the motion, and generate a new AI video clip using both images as endpoint guides. Free first and last frame AI video generator.Open workflow
- AI Video ExtenderUpload a source clip and describe what happens next. FrameAI generates a reference-guided AI video extension that matches the original style and motion. Free AI video extender online.Open workflow
AI video workspace — every input in one place
Text, image, and reference inputs share one workspace. Set length, ratio, resolution, and audio, then review the maximum credit reservation before you generate.
With Seedance 2.5, FrameAI supports 480p through 720p, synchronized audio, seven aspect ratios, and commercial use with paid access under the Terms of Service. The maximum credit reservation is shown before generation; successful video jobs can settle lower from provider-reported usage, and confirmed failed jobs return the reservation.
- Text, images, and video in one generator
- Up to 720p with synchronised audio
- Commercial use with paid access
What the unified workspace supports
Every generation mode in one workspace — text to video, image to video, and reference to video.
Start from a picture
Upload a photo, a product shot, an illustration or a frame, and describe what should happen. The image anchors the look while the prompt supplies the movement - a direct way to bring a specific real object into motion.
Start from footage
Feed in up to 10 video clips and 10 audio files as references. Seedance 2.5 can use their motion, pacing, camera style, or sound as guidance for a new scene.
How the workspace brings it together
A video model does not assemble frames one after another the way an editor does. It generates the whole clip as a single object, denoising it from a compressed representation while every frame is conditioned on every other frame plus on whatever you supplied - your text, your images, your reference footage. That is why temporal consistency is a property of the model rather than something you fix in post, and why a subject can stay recognisably itself while the camera moves around it.
The practical lesson is that prompts should describe a shot, not a story. Seedance 2.5 has 4 to 30 seconds per generation; it can execute one clear action with one clear camera behaviour beautifully, and it will make a mess of five plot beats crammed into a paragraph. Write like a director filling in a shot list - subject, action, camera, light, mood - and reach for the extend and transition tools when a sequence genuinely needs to be longer than one take.
Describe one shot
"Slow dolly-in on a barista pouring latte art, warm window light, shallow depth of field" beats a paragraph of narrative. Concrete nouns and camera verbs do the work.
Change one thing at a time
When a result is close but wrong, edit a single variable and regenerate. Rewriting everything teaches you nothing about which word actually mattered.
Model specifications
Seedance 2.5 AI video specifications on FrameAI
Published model limits, not marketing rounding. Every number below is enforced by the generator before your credits are reserved.
- 480p / 720p
- Output resolutions on this model — up to 4K across FrameAI models
- 4-30 sec
- Clip length per generation, at 24 fps
- Native audio
- Sound effects and ambience generated in sync
- 30 + 10 + 10
- Reference images, videos, and audio files per request
- 7 ratios
- Supported aspect ratios - Auto, 16:9, 4:3, 1:1, 3:4, 9:16, 21:9
- Commercial use with paid access
- Subject to the Terms of Service
Why creators use FrameAI for AI video generation
The model is ByteDance's. What FrameAI adds is what makes it usable at work: honest limits, honest billing, and output you are allowed to ship.
Text, images, and video in a single pass
Text, up to 30 reference images, 10 reference videos, and 10 audio references can guide one Seedance 2.5 generation instead of being stitched together afterwards.
Sound generated with the picture
When audio is enabled, Seedance 2.5 can generate footsteps, room tone, impacts, dialogue, and score with the video. Review timing and content before publishing, or switch audio off when the clip needs separate sound design.
Flexible ratios, up to 4K
One prompt covers a 9:16 vertical cut for Reels, a 16:9 master for YouTube, and a 21:9 anamorphic frame for a title sequence. Resolution runs from 480p to 4K, so the same take holds up on a cinema screen and on a phone.
Credits you can predict
The maximum credit reservation is calculated from the selected model, duration, resolution, ratio, and video-reference input, then shown before submission. A successful video job can settle lower from provider-reported usage; confirmed failed jobs return the reservation.
Built for efficient iteration
Use Mini for cost-efficient prompt exploration, Fast when you want a balance of generation speed and cost, and Seedance 2.5 when its longer duration or richer reference inputs fit the shot. Switching models starts a new generation, so results may vary.
Yours to sell
Content generated with a paid subscription or purchased credit pack may be used commercially under the Terms of Service. Content generated solely with free sign-up or promotional credits is for evaluation and personal use only.
Create a video in three steps
From blank page to downloadable clip, without opening an editing suite.
- 1
Describe the shot
Type what should be on screen, in English or Chinese. Attach up to 30 images, 10 videos, or 10 audio references when they help guide the shot.
- 2
Choose your output
Set the aspect ratio for wherever this is going, a duration between 4 and 30 seconds, and a resolution from 480p to 720p. The maximum credit reservation updates with your settings before submission.
- 3
Generate and download
The job runs in the background and lands in My Creations. Output generated with a paid subscription or purchased credit pack may be used commercially under the Terms of Service; if generation fails, the credits return automatically.
Where the unified workspace saves time
The wins are where volume, speed or cost used to make video impossible - not where a film crew was already the right answer.
Marketing that needs ten versions
Generate advertising, seasonal, and localised variants in the required aspect ratio without scheduling a new shoot. Each request is a separate generation, and generation time varies with settings and provider load.
Product and e-commerce video
An existing product photo can guide a rotating hero shot, lifestyle scene, or detail pass without a new shoot. Packaging, logos, text, and small details can still change, so review every frame.
Concepts, pitches and prototypes
Showing a client the film beats describing it. Generating pre-visualisation at 720p makes an idea concrete before any real budget is committed to it.
AI video maker — frequently asked questions
What is an AI video generator?
It is a model that produces video directly from your inputs - text, images, reference footage, and supported audio references - rather than editing existing clips together. FrameAI runs Seedance 2.5, which generates 4-to-30-second clips at up to 720p with synchronised audio.
Do I need video editing experience?
No. There is no timeline, no keyframing and no plugin chain. You write a description, choose a ratio and length, and press generate. The skill that helps is describing a shot precisely, which is learned in a handful of attempts.
How long can the generated videos be?
Each Seedance 2.5 generation produces 4 to 30 seconds at 24 fps. For longer pieces, use Video Extend to continue a clip or Video Transition to join two takes - building a sequence from good shots works far better than asking for one very long one.
Does the generated video include sound?
Yes. Seedance 2.5 can generate sound effects, ambience, dialogue, and score with the picture. Review timing and content before publishing, or turn audio generation off if you plan to score the clip yourself.
How much does it cost?
The maximum credit reservation depends on the model, duration, resolution, aspect ratio, and whether video references are included. FrameAI shows that reservation before submission. After a successful job, provider-reported usage can lower the final charge and unused credits are returned. Confirmed failed jobs return the reservation.
Can I use the videos commercially?
To the extent permitted by applicable law, FrameAI does not claim ownership of videos you generate. Videos generated with a paid subscription or purchased credit pack may be used commercially under the Terms of Service. Videos generated solely with free sign-up or promotional credits are for evaluation and personal use only.
Explore more AI video tools
Each tool uses Seedance 2.5 for a different job. Move between them freely — your credits, history, and exports are shared.
Seedance 2.5Seedance 2.5 flagship AI video modelSeedance 2.0Seedance 2.0 high-resolution 4K video modelText to VideoFree text to video AI generatorImage to VideoFree image to video AI generatorAI Reference-to-Video GeneratorMulti-reference AI video generatorVideo to VideoAI video restyling & transformationAI Multi-Shot Video GeneratorAI multi-shot video generator for cinematic sequences
Ready to put AI video into your content workflow?
Choose paid access when you need commercial-use eligibility, predictable generation costs, and credits restored after a failed or rejected job. One-time packs are available with no subscription.
- One-time credit packs never expire
- Commercial use with paid access
- Reserved credits restored if generation fails