Seedance 2.5 Text to Video

ByteDance / Seedance 2.5 Text to Video — Text to Video (seedance-2.5-t2v)

Seedance 2.5 text-to-video generates cinematic videos from text prompts with output up to 30 seconds. Optionally include image, video, and audio references for creative guidance.

亮点

• •Extended Duration – Generate videos from 4 up to 30 seconds in a single request.
• •Multi-Reference – Combine up to 9 images, 3 videos, and 3 audio files as creative references.
• •Native Audio – Synchronized audio generation with lip-sync, sound effects, and ambient sounds.
• •Improved Consistency – Better reference understanding and cinematic language than Seedance 2.0.

参数

• •prompt* – Text description of the video to generate. Reference uploaded files with @Image 1, @Video 1, @Audio 1 syntax.
• •aspect_ratio – Video aspect ratio
  • • 16:9 (Landscape)
  • • 9:16 (Portrait)
  • • 1:1 (Square)
  • • 4:3
  • • 3:4
  • • 21:9 (Ultrawide)
  • • Adaptive
• •duration – Video duration in seconds (4-30)
• •resolution – Video resolution
  • • 480P
  • • 720P
• •generate_audio – Generate synchronized AI audio (included in base cost)
• •reference_image_urls – Reference images (max 9). Formats: jpeg, png, webp, bmp, tiff, gif. Max 30MB each.
• •reference_video_urls – Reference videos (max 3). Formats: mp4, mov. Max 50MB each.
• •reference_audio_urls – Reference audio files (max 3). Formats: wav, mp3. Max 15MB each.

定价

如何使用

1. 1.Write a detailed prompt describing the video you want to generate.
2. 2.Optionally upload reference images, videos, or audio files for style/content guidance.
3. 3.Use @Image 1, @Video 1, @Audio 1 syntax in prompts to reference uploaded files.
4. 4.Configure aspect ratio, duration, and resolution.

更多可试用的模型