Model Introduction
The Seedance 2.5 model supports direct output of 30-second single-segment videos, with up to 50 reference materials (images/audio/videos) per input. It features stronger instruction control, professional-level controllable video editing and extension capabilities; meanwhile, it natively supports generating content in more than 10 languages, ensuring professional-level narrative stability in global scenarios, ushering video generation into an industrial-grade new stage of "long narrative × strong reference × precise editing × multilingual".
This article introduces the unique capabilities and usage methods of the Seedance 2.5 model to help you quickly implement the Create Video Generation Task API call.
Latest Capabilities
- Video Duration Doubled The maximum video generation duration has been extended from 15 seconds to 30 seconds.
- Increased Reference Material Count
- Reference image limit increased from 9 to 30
- Reference audio/video limit increased from 3 to 10
- Reference audio/video total duration increased from 15 seconds to 30 seconds
- Smarter Aspect Ratio/Duration Control
- For video editing tasks, the output video's aspect ratio and duration are automatically kept consistent with the input video.
- For video extension and first frame/first & last frame tasks, the output video's aspect ratio is automatically kept consistent with the input video.
- New MOV Output Format Added MOV format (H.264 video encoding + yuv444p chroma sampling + PCM audio encoding) for output videos, improving color fidelity and audio-visual consistency in video editing and extension scenarios.
- Native Multilingual Support Supports 11 languages: Chinese, English, Spanish, Indonesian, Malay, Thai, Arabic, Portuguese, Vietnamese, Japanese, and Korean.
Model Capabilities
| Model Name | Seedance 2.5 | Seedance 2.0 | Seedance 2.0 fast | Seedance 2.0 mini | |
|---|---|---|---|---|---|
| Model ID | doubao-seedance-2-5-260628 | doubao-seedance-2-0-260128 | doubao-seedance-2-0-fast-260128 | doubao-seedance-2-0-mini-260615 | |
| Text-to-Video | ✓ | ✓ | ✓ | ✓ | |
| First Frame to Video | ✓ | ✓ | ✓ | ✓ | |
| First & Last Frame to Video | ✓ | ✓ | ✓ | ✓ | |
| Multi-Modal Reference | Image Reference | ✓ | ✓ | ✓ | ✓ |
| Multi-Modal Reference | Video Reference | ✓ | ✓ | ✓ | ✓ |
| Multi-Modal Reference | Audio Reference | ✓ | × (requires image/video) | × (requires image/video) | × (requires image/video) |
| Multi-Modal Reference | Combined Reference: • Image + Audio • Image + Video • Video + Audio • Image + Video + Audio | ✓ | ✓ | ✓ | ✓ |
| Edit Video | ✓ | ✓ | ✓ | ✓ | |
| Extend Video | ✓ | ✓ | ✓ | ✓ | |
| Generate Video with Audio | ✓ | ✓ | ✓ | ✓ | |
| Reference Material Limit | 50 (30 images + 10 videos + 10 audios) | 15 (9 images + 3 videos + 3 audios) | 15 (9 images + 3 videos + 3 audios) | 15 (9 images + 3 videos + 3 audios) | |
| Web Search Tool | ✓ | ✓ | ✓ | ✓ | |
| Draft Mode | ✓ | × | × | × | |
| Return Last Frame | ✓ | ✓ | ✓ | ✓ | |
| Output Video Specs | Output Resolution | 480p, 720p, 1080p | 480p, 720p, 1080p, 4k | 480p, 720p | 480p, 720p |
| Output Video Specs | Output Aspect Ratio | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive |
| Output Video Specs | Output Duration | 4~30 seconds; -1 (model automatically selects optimal duration within valid range) | 4~15 seconds; -1 (model automatically selects optimal duration within valid range) | 4~15 seconds; -1 (model automatically selects optimal duration within valid range) | 4~15 seconds; -1 (model automatically selects optimal duration within valid range) |
| Output Video Specs | Output Video Format | mp4, mov | mp4 | mp4 | mp4 |
| Offline Inference | × | × | × | × |
Task Types and Special Restrictions
Note
Seedance 2.5 will classify requests into 5 task types: text-to-video, reference-based video generation, video editing, video extension, and first frame/first & last frame video generation based on the content.role parameter values and prompt intent.
- If the task type is video editing, video extension, or first frame/first & last frame video generation, the model has special restrictions on aspect ratio and duration parameters. Violating these restrictions will trigger asynchronous errors. Please refer to the trigger conditions and special restrictions for each task type below when setting parameters.
- If the task type is text-to-video or reference-based video generation, the model has no special restrictions on aspect ratio and duration parameters; however, avoid using words related to video editing or extension in the prompts of reference-based video generation tasks to prevent the model from misjudging and triggering errors.
| Task Category | Task Description | Task Trigger Conditions (Two-Level Judgment) | Special Restrictions |
|---|---|---|---|
| Video Editing | Edit the visuals or audio of the original video (e.g., replace video subjects, add/remove/modify objects in video, local redraw/repair, etc.) | 1. Parameter content.role must be set to reference_image / reference_video / reference_audio2. Prompt trigger keywords (containing any one of them): edit video, add/append, delete/remove, modify/replace/change to Example: Add some small animals to @video1; Change the character in @video1 to @image1; Remove the background music from @video1 | - Aspect Ratio: Only supports setting parameter ratio to adaptive; the model automatically keeps the output video's aspect ratio consistent with the video to be edited; no other settings are supported- Duration: Only supports setting parameter duration to -1; the model automatically keeps the output video's duration basically consistent with the video to be edited; no customization is supported |
| Video Extension | Extend the original video forward/backward | 1. Parameter content.role must be set to reference_image / reference_video / reference_audio2. Prompt trigger keywords (containing any one of them): extend forward/backward, continue, continue writing Example: Extend @video1 backward, character from @image1 descends from the sky...; Continue writing the first 5s of @video1, woman in @video2 enters the frame and says... | - Aspect Ratio: Only supports setting parameter ratio to adaptive; the model automatically keeps the output video's aspect ratio consistent with the video to be extended; no other settings are supported |
| First Frame / First & Last Frame Video Generation | Input 1 image as the first frame to generate a video, or input 2 images as the first and last frames respectively to generate a video | Parameter content.role must be set to first_frame / last_frame | - Aspect Ratio: Only supports setting parameter ratio to adaptive; the model automatically matches the aspect ratio; no other settings are supported |