Generate from text, first/last frames, or as many as 50 multimodal references, or continue and edit one source video.
Start from text, animate a first frame with an optional ending frame, combine multimodal references, or continue and edit one MP4 with optional image and audio guidance.
Final charge uses the greater of input video duration rounded to the nearest whole second or the applicable minimum, plus output duration.
Similar Models
Model overview
Seedance 2.5 on sjolt exposes text-to-video, image-to-video, reference-to-video, video-extend, and video-edit routes. Start from text, animate a first frame with an optional last frame, guide a generation with multimodal references, or continue and edit one MP4 source with up to 30 images and 10 audio references through the asynchronous task API.
Generate any whole-second duration from 4 through 30. Use the longer timeline to build a complete scene with an opening, development, camera progression, synchronized sound, and a deliberate ending instead of stitching together several short clips.
Combine up to 30 images, 10 MP4 clips, and 10 audio files in one reference-guided request. Assign each source a role with @ mentions to preserve characters and products, borrow camera movement, match visual style, and coordinate dialogue, music, or ambience.
Describe changes at specific moments and anchor them with reference frames, clips, and audio cues. Target a character, action, prop, background, or sound beat while helping the surrounding identity, motion, lighting, and audiovisual continuity remain coherent.
Model characteristics
Plan a complete narrative or visual arc with enough time for scene development, measured camera movement, transitions, and a resolved ending.
Bring together 30 images, 10 videos, and 10 audio files for identity, style, motion, camera, dialogue, and sound guidance.
Use time-ordered instructions and multimodal anchors to focus changes on a particular moment or visual element while maintaining continuity around it.
FAQ
Seedance 2.5 is a ByteDance video model with separate routes for prompt-only generation, first/last-frame animation, multimodal reference guidance, source-video extension, and source-video editing.
Reference-to-video accepts up to 30 PNG, JPG, JPEG, or WebP images, 10 MP4 videos, and 10 MP3, WAV, M4A, AAC, or OGG audio files. Each video must be 2 to 30 seconds, and all videos together must not exceed 30 seconds. Video extension and video editing each require exactly one MP4 and also accept up to 30 images and 10 audio files.
The text-to-video route does not accept reference files. Image-to-video requires a first frame and accepts an optional last frame. Reference-to-video requires at least one image, video, or audio URL. Video extension and video editing each require exactly one video URL; their image and audio references are optional.
Text, image, reference, and video-extension generation support a whole-second duration from 4 to 30 and 480p, 720p, 1080p output. Text-to-video supports 16:9, 9:16, 1:1, 3:4, 4:3, 21:9 framing; reference-to-video additionally supports adaptive framing, image-to-video follows the first-frame aspect ratio, video extension follows its source framing, and video editing determines framing and length from its source.
State what must remain stable, assign each uploaded reference a role, then describe the action, camera movement, scene changes, lighting, and sound in chronological order.
Submit the text-only, image-guided, reference-guided, video-extend, or video-edit request to its dedicated endpoint. Poll the returned task ID, then read the generated MP4 URL from the successful task result.
