kiira.ai text-to-video and image-to-video using ByteDance Seedance 2.0 (videa ai).

Seedance 2.0

kiira.ai text-to-video and image-to-video using ByteDance Seedance 2.0 (videa ai).

← Home

Video

Seedance 2.0
0 / 2000
Reference video0 / 3

Reference videos for motion transfer, style reference, and editing (up to 3 files, combined duration up to 15 seconds). Reference them in the prompt, e.g. [Video1], [Video2].

Default: []

Reference audio0 / 3

Reference audio for audio-driven generation and lip-sync (up to 3 files, combined duration up to 15 seconds). Requires at least one reference image or video. Reference in the prompt, e.g. [Audio1], [Audio2].

Default: []

6s
Resolution

Optional. Same seed and settings help reproduce similar results.

Generate audio

Credits: 540360

Please sign in with Google (top right) to generate images.

Sample video

(Generated video will appear here)

Videa AI: Seedance 2.0 uses a unified multimodal architecture with text, image, and audio inputs for high-quality video generation. It lets you precisely control environmental factors such as shadows and lighting, plus cinematic elements including dolly zoom and complex character motion.

How to use this studio

  1. Choose a mode

    Pick Text to video for prompt-only runs, or Image to video when you need a first frame (and optionally a last frame) or reference images / reference media.

  2. Set parameters

    Select aspect ratio, resolution, duration, and whether to generate audio. Use a fixed seed when you want reproducible results; leave it empty for random.

  3. Write the prompt & references

    Describe motion, camera, lighting, and dialogue (use double quotes for lines you want spoken). For reference video/audio, follow the on-page hints and tag clips as [Video1] / [Audio1] in the prompt.

  4. Sign in & generate

    Sign in with Google, confirm the credit estimate, then run. When the clip is ready, it appears in the preview player for playback and download.

Use cases

Marketing & social shorts

Turn a product still or tagline into a vertical or horizontal promo clip with controlled pacing and lighting.

Storyboards & previs

Block out shots from text or keyframes before spending time on full production pipelines.

Character motion from a still

Animate portraits or mascots while keeping identity consistent when paired with clear prompts and references.

Audio-driven lip sync

When reference audio is enabled and paired with visuals, align mouth movement and ambience to your script.

FAQ

Do I need an account to generate?

Yes. Sign in with Google so we can attach generations to your account and credit balance.

What inputs does image-to-video support?

Keyframe mode uses a required start image and an optional end image. Reference mode accepts multiple reference images plus optional reference videos and audios within the limits shown in the form.

How are credits calculated?

Credits depend on resolution, duration, audio generation, and reference media. The studio shows an estimate before you run; see Pricing for packs and subscriptions.

Why did my request fail with a content warning?

Prompts or media may violate safety policies. Revise the prompt, remove sensitive references, and try again.

Where can I learn more about the model?

Open the Seedance overview page from the top navigation for capabilities, examples, and workflow tips.