Text to video with cinematic camera control
Describe subject, action, lighting, lens, mood, and camera language in the prompt. These terms guide a separate new generation rather than providing a deterministic camera or motion path.
An example of what this page produces.
Seedance 2.0
Seedance 2.0 high-resolution 4K video model
Seedance 2.0 high-resolution 4K video model
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
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
Your generated video appears here. Describe a shot and hit Generate.
Generate videos at up to 4K with synchronized sound using Seedance 2.0 on 智擎云. Combine text prompts, reference images, and reference video clips in one generation.
On 智擎云, Seedance 2.0 supports output up to 4K, seven aspect ratios, up to nine reference images with three reference videos in reference mode, and optional generated audio. The maximum credit reservation is shown before submission; successful jobs can settle lower from provider-reported usage, and confirmed failed jobs return the reservation. Paid-access commercial use remains subject to the Terms of Service.
Seedance 2.0 is designed for high-fidelity generation from text, images, and reference clips, with native audio in a single pass.
Describe subject, action, lighting, lens, mood, and camera language in the prompt. These terms guide a separate new generation rather than providing a deterministic camera or motion path.
In Reference to Video, combine up to nine images and three reference clips in one request. They can guide identity, product, palette, and motion, but the generated take may still change composition and fine details.
When enabled, generated foley, room tone, dialogue, and score arrive with the video. Review timing and content before publishing, or disable audio when the clip needs a separate sound-design pass.
On 智擎云, Seedance 2.0 accepts a prompt plus either opening-frame guidance or a reference set of images and clips. These input modes are separate: Reference to Video can combine up to nine images and three clips, while Image to Video uses a required opening frame with an optional closing frame. All references guide a newly generated result rather than locking identity, motion, or composition.
Prompts and references can guide identity, camera language, lighting, and motion, but each run remains independent and details can drift. When audio is enabled, the provider generates it with the video; review timing, dialogue, and content rather than assuming frame-level alignment. On 智擎云 each generation is 4 to 15 seconds at 24 fps.
智擎云 currently accepts text, image, and video inputs: a prompt, up to nine reference images, and up to three reference clips can guide one generation. When sound is enabled, it is generated with the picture rather than supplied as an input.
Choose Seedance 2.0 for the flagship tier and output up to 4K, Fast for the provider-positioned balance of generation speed and cost at up to 720p, or Mini for cost-efficient 480p and 720p iteration. 智擎云 shows the maximum credit reservation before submission; successful jobs can settle lower from provider-reported usage.
When audio is enabled, Seedance 2.0 can generate foley, ambience, impacts, dialogue, and score with the picture. Treat the audio as generated output: review timing, content, and copyright restrictions, or switch it off when separate sound design is required.
Model specifications
Published model limits, not marketing rounding. Every number below is enforced by the generator before your credits are reserved.
The model is ByteDance's. What 智擎云 adds is what makes it usable at work: honest limits, honest billing, and output you are allowed to ship.
Text, up to 9 reference images, 3 reference videos, and 3 audio references can guide one Seedance 2.0 generation instead of being stitched together afterwards.
When audio is enabled, Seedance 2.0 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.
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.
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.
Use Mini for cost-efficient prompt exploration, Fast when you want a balance of generation speed and cost, and Seedance 2.0 when its longer duration or richer reference inputs fit the shot. Switching models starts a new generation, so results may vary.
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.
No timeline, no keyframes, no editing software. Describe your shot in plain language and generate a finished video clip online.
Describe subject, action, and camera in a focused prompt, then choose either frame guidance or a reference set. Product stills, faces, and clips can guide the result, but they do not lock identity, motion, or composition.
Pick from seven aspect ratios, a 4-to-15-second duration, and 480p through 4K. The maximum credit reservation updates with your settings before submission; a successful job can settle lower from provider-reported usage. Generated audio is on by default and can be switched off.
Press generate and the job runs in the background - the result waits in My Creations. Output generated with a paid subscription or purchased credit pack may be used commercially under the Terms of Service. If the provider fails the job, your credits come back.
Marketing teams, content creators, and studios are replacing crew-and-location shoots with a text prompt and an afternoon of iteration.
Growth teams can generate variants of one product spot with different hooks, aspect ratios, and pacing. Attaching the product photo helps guide packaging and product appearance, but logos, labels, and fine details can still change, so review every variant before an ad test.
Generate a 9:16 vertical video with optional ambience and impacts in the same task. Review audio timing, dialogue, and content before publishing to TikTok, Instagram Reels, or YouTube Shorts.
Directors and creative agencies can use 4K AI-generated takes to explore an idea before committing production budget. Reference images and clips guide visual style and camera motion, but every result remains a separate generation that should be reviewed for drift.
Seedance 2.0 is ByteDance's second-generation video foundation model. On 智擎云 it accepts text, up to nine reference images, and up to three reference video clips, then generates 4-to-15-second clips at up to 4K with synchronized sound. 智擎云 supports all seven aspect-ratio options.
The maximum credit reservation depends on model, duration, resolution, aspect ratio, and video-reference input, and is displayed 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.
智擎云 accepts a text prompt in English or Chinese, up to nine reference images, and up to three reference video clips in one request. Text works by itself; images and video add visual, subject, motion, or camera guidance.
Resolutions are 480p, 720p, 1080p and 4K. Aspect ratios are 16:9, 9:16, 21:9, 1:1, 4:3, 3:4 and adaptive, which lets the model match the shape of your reference material. Seedance 2.0 Fast and Seedance 2.0 Mini are capped at 720p - that ceiling is the provider’s, and the generator enforces it rather than letting a job fail upstream.
To the extent permitted by applicable law, 智擎云 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.
On 智擎云, Seedance 2.0 combines text, image, and video guidance in one generation, produces synchronized sound instead of a silent file, and supports output up to 4K across seven aspect-ratio options.
Be specific about subject, action, camera, light, and mood instead of relying on vague qualifiers. A concrete prompt gives you clearer variables to review, but no wording guarantees a particular result. If a generation drifts from your intent, reduce it to one action and add detail back one element at a time.
Seedance 2.0 generates clips of 4 to 15 seconds per request. For longer sequences, Video Extend creates a separate reference-guided continuation and Video Transition generates a new clip between two endpoint images. Both workflows can drift and require review before assembly.
Each tool uses Seedance 2.0 for a different job. Move between them freely — your credits, history, and exports are shared.
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.