Seedance 2.5 示例 1
The actress from @Image1 as the main subject. Reference @Video1 for rhythmic push-pull-pan-tilt camera work. The actress mirrors the dance movements from @Video1's female dancer, performing energetically on stage.
Seedance 2.5 每次生成最多可接收 2 张参考图,让输出更准确地遵循关键视觉素材。
可在模型支持范围内选择 480p、720p、1080p,默认使用 720p,便于兼顾速度和细节。
7 种宽高比和 27 种时长会在提交任务前完成校验。
Seedance 2.5 可以随视频生成声音,在一次工作流中保持画面和音频要求一致。
Seedance 2.5 AI 视频生成器可满足多种专业与创作需求:
| 功能 / 模型 | Seedance 2.5 | Seedance 2.0 | HappyHorse 1.1 |
|---|---|---|---|
| 时长 | 4–30 秒 | 4–15 秒 | 3–15 秒 |
| 分辨率 | 480p / 720p / 1080p | 480p / 720p / 1080p / 4K | 720p / 1080p |
| 宽高比 | auto / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 | auto / 16:9 / 9:16 / 1:1 | 16:9 / 9:16 / 1:1 / 4:3 / 3:4 |
| 参考图 | 最多 2 张 | 最多 2 张 | 最多 1 张 |
| 原生音频 | 支持 | 支持 | 支持 |
| 起始积分 | 462 | 304 | 241 |

The actress from @Image1 as the main subject. Reference @Video1 for rhythmic push-pull-pan-tilt camera work. The actress mirrors the dance movements from @Video1's female dancer, performing energetically on stage.
The character in the painting has a guilty expression, glances left and right, then reaches out of the frame to grab a cola and takes a sip with a satisfied look. Hearing footsteps, the character quickly puts the cola back. A cowboy picks up the cola and walks away. The camera pushes forward to a pure black background with a spotlight on the canned cola, with artistic subtitles: "Yikou Cola, a must-try!"
The man (@Image1) walks wearily down a corridor after work, his pace slowing. He stops at his front door, close-up shot of his face as he takes a deep breath, adjusts his emotions, puts on a relaxed expression. Close-up of him finding his keys, inserting the lock. After entering, his little daughter and pet dog run joyfully to greet and hug him. The interior is very warm and cozy, with natural dialogue throughout.
Reference the model's facial features from the first image. The model wears the outfits from reference images 2-6, approaching the camera with playful, cool, cute, surprised, and stylish poses.
Reference Video1's audio, using Image1-5 as inspiration to create an emotionally-driven video. Background music references @Video1.
Extend the video by 15 seconds. Reference @Image1 and @Image2's donkey-on-motorcycle character for a wild ad sequence.
在 seedance ai 用 Seedance 2.5 把创意变成视频。