Seedance 2.5 can use text, images, video, and audio as creative context. APIXO supports up to 30 images, 10 video clips, and 10 audio clips in omni-reference mode.
Seedance 2.5 is ByteDance’s audiovisual video model for longer, reference-driven storytelling. It combines timeline-based direction, multimodal creative guidance, synchronized sound, multilingual performance, and selective revision to help production teams develop connected scenes instead of isolated short clips.
Inputs
Text / Image / Video / Audio
APIXO Price
From $0.085 / Second
Duration
Up to 30 Seconds
References
30 Images / 10 Videos / 10 Audio
Editing
Timestamp-Level Control
Loading workspace...
Provider demonstrations show an approximately 30-second sequence moving through several environments while maintaining a readable lead subject, connected camera movement, and deliberate visual transitions.
Organize actions, camera changes, scene transitions, dialogue, and sound cues around specific moments to give longer creative briefs a clearer narrative structure.
Combine written instructions with visual, motion, and audio material to communicate subject appearance, environment, performance, camera language, rhythm, or sound direction.
Official examples combine moving subjects with speech, music, ambience, and effects, supporting concepts in which visual action and sound must develop together.
A provider-selected demonstration presents spoken performance across multiple languages with corresponding visible mouth movement, music, and coordinated scene changes.
Demonstrated editing behavior can target an unwanted scene element while attempting to retain the useful protagonist, framing, and camera motion around it.
ByteDance
Provider
Multimodal Guidance
Input
Video + Audio
Output
Timeline Direction
Story Control
Selective Revision
Editing
3 Generation Modes
APIXO Controls
Coordinate product reveals, environment changes, camera movement, music, dialogue, and sound effects across a longer campaign sequence. Use timeline-based direction to align key actions with specific moments while maintaining a coherent audiovisual progression.
Follow a recurring subject through connected locations, actions, and visual phases in sequences of up to 30 seconds. Use the output for treatments, pitches, storyboards, and previsualization before committing to full production.
Combine character images, product references, motion footage, audio samples, and written art direction to coordinate subjects, environments, performances, camera language, rhythm, and sound within one generation.
Revise selected moments through timestamp-level instructions instead of rebuilding the complete sequence. Explore background changes, object removal, styling adjustments, perspective changes, and other localized audiovisual edits.
APIXO supports fixed Seedance 2.5 durations from 4 to 30 seconds and dynamic duration. Dynamic requests reserve 30 output seconds and settle to the actual successful result.
The upstream model supports up to 30 image references, 10 video references, and 10 audio references in one generation. Assign every source a clear role and avoid conflicting instructions.
Timestamp-level editing provides more focused control over selected moments but does not guarantee that surrounding frames, sound, or scene details will remain completely unchanged.
References guide identity, appearance, movement, camera behavior, voice, sound, and style, but do not guarantee exact preservation of people, products, typography, logos, materials, or geometry.
Review anatomy, hands, object contact, rapid movement, scene transitions, occlusion, dialogue, pronunciation, speaker consistency, and audiovisual synchronization before publication.
APIXO exposes text-to-video, first-and-last-frames, and omni-reference modes with 480p or 720p output in MP4 or MOV format.
Seedance 2.5 can use text, images, video, and audio as creative context. APIXO supports up to 30 images, 10 video clips, and 10 audio clips in omni-reference mode.
APIXO supports fixed output from 4 to 30 seconds, plus dynamic duration for workflows whose final length should be selected by the generation system.
Yes. Seedance 2.5 supports timestamp-level revision and reference-guided operations such as targeted scene changes, object removal, green-screen concepts, perspective adjustments, and motion-led editing.
Yes. Enable sound to generate dialogue, music, ambience, and effects together with the visual sequence. Omni-reference also accepts up to 10 audio files of 2–30 seconds each.
No. References communicate creative intent but cannot guarantee exact identity, typography, logos, voice, materials, proportions, motion, or product geometry. Review all production assets before release.
Discover more AI models for your next creative workflow
Seedance 2.0 is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Seedance 2.0 Fast is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Seedance 2.0 Mini is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
HappyHorse is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
MiniMax H3 is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Gemini Omni is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Wan 2.7 is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Kling 3.0 Std is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Video
