ByteDance · Video models
Seedance 1.5
Seedance 1.5 is ByteDance’s image-to-video model, running as one of the shot generators inside a Scenema long-form video.
200 credits on signup, then weekly refills through your first month. No credit card required.
Seedance 1.5 on Scenema
Seedance 1.5 is ByteDance’s image-to-video model, built on the dual-branch diffusion transformer architecture behind the Seedance family and tuned for smooth motion from a single reference frame. On Scenema, Seedance 1.5 runs as an image-to-video shot generator inside the long-form video pipeline. Seedance 1.5 delivers the take at up to 720p, from 4 to 12 seconds, always driven by a reference image. Scenema packs those takes into scenes, and scenes into full-length videos with character consistency, voiceover, and music running across every cut.
Specifications
Seedance 1.5 specifications on Scenema
- Supports
- Image to video
- Duration
- 4 to 12 seconds
- Resolution
- Up to 720p
- Aspect ratios
- 16:9, 9:16, and 1:1
- Quality tier
- Standard
Distinctive
What makes Seedance 1.5 distinctive
Seedance 1.5 is image-to-video only on Scenema.
Every generation starts from a reference frame, which anchors composition, character, and lighting before the motion is generated.
Seedance 1.5 delivers smooth motion from a still.
The Seedance family uses a diffusion transformer trained for stable subject motion, useful when the starting frame already defines the shot.
Seedance 1.5 covers the standard aspect ratios.
Shots can be generated in 16:9, 9:16, or 1:1, so the same reference image can drive landscape, vertical, and square variants of a scene.
Scenema assembles Seedance 1.5 shots into long-form video.
Each Seedance 1.5 generation is one shot inside a Scenema scene. Scenema plans the shot list, feeds the right reference frame to each generation, and assembles the shots into full videos with continuous character, voiceover, and music tracks.
Use cases
Use cases for Seedance 1.5
Seedance 1.5 animates existing key art.
Turn a hero image, a storyboard frame, or a still render into a moving shot inside a longer video.
Seedance 1.5 fits reference-locked shots.
Use Seedance 1.5 when the composition and character are already set by the input image and only the motion needs to be generated.
Seedance 1.5 handles B-roll from stills.
Convert product photos or location stills into short takes that slot into a Scenema scene.
Seedance 1.5 supports iteration on a fixed frame.
Try multiple motion variants of the same reference image before promoting one into the final video.
Compare
How Seedance 1.5 compares to other video models
See where Seedance 1.5 slots in the lineup on the axes that matter most.
| Model | Best for | Shot length | Max resolution | Inputs | Quality tier |
|---|---|---|---|---|---|
| Veo 3.1 | Google DeepMind Veo 3.1 as the cinematic shot generator inside a Scenema long-form video. | 4, 6, or 8 seconds | Up to 1080p | Text to video, Image to video | High |
| Kling 3.0 | Kling 3.0 is Kuaishou’s flagship generative video model, running as one of the shot generators inside a Scenema long-form video. | 4, 6, 8, 10, or 12 seconds | 1080p | Text to video, Image to video | High |
| Seedance 2.0 | Seedance 2.0 is ByteDance’s multimodal video model, running as one of the shot generators inside a Scenema long-form video. | 4 to 15 seconds | Up to 720p | Text to video, Image to video, Audio to video | High |
| Seedance 1.5 | Seedance 1.5 is ByteDance’s image-to-video model, running as one of the shot generators inside a Scenema long-form video. | 4 to 12 seconds | Up to 720p | Image to video | Standard |
| Wan 3.0 | Wan 3.0 is Alibaba’s third-generation Tongyi Wanxiang video model, running as one of the image-to-video shot generators inside a Scenema long-form video. | 4 to 12 seconds | 720p | Image to video | High |
| MiniMax H3 | MiniMax H3 is the video model Scenema uses for shots with complex motion and many different characters, props, and places that all have to stay consistent. | 4 to 15 seconds | 768p | Image to video, Reference to video | High |
| Vidu Q3 Turbo | Vidu Q3 Turbo is a start-and-end-frame video model on Scenema, tuned for shots that must land on an exact ending composition. | 1 to 15 seconds | 720p | Image to video | Standard |
| Gemini Omni Flash | Gemini Omni Flash is Google’s multimodal video model, running as one of the shot generators inside a Scenema long-form video. | 4, 6, 8, or 10 seconds | Up to 4K | Image to video | High |
| LTX 2.3 | LTX 2.3 is Lightricks’ open video foundation model, hosted on Scenema with a Fast tier for iteration and a Pro tier for delivery-quality takes. | 4 to 12 seconds | Up to 1080p | Text to video, Image to video, Audio to video | Fast and Pro tiers |
Where it fits
Where Scenema uses Seedance 1.5
Scenema runs a highly optimized workflow and uses the best model for the style and for each task under the hood. You choose the quality and the resolution. Here is where Seedance 1.5 fits and where a different model does.
- 1
Scenema uses Seedance 1.5 when the shot starts from a locked reference image.
Seedance 1.5 is image-to-video only. If you already have the exact frame you want the shot to open on, Seedance 1.5 animates from that frame without the drift that text-to-video introduces.
- 2
Scenema uses Seedance 1.5 when you need many image-to-video takes at a lower cost than 2.0.
Seedance 1.5 is a standard-tier model. For batch work off a locked keyframe, such as animating a set of product stills or character poses, it delivers usable motion at a lower cost per generation than Seedance 2.0.
- 3
Scenema uses Seedance 1.5 when the shot is up to 12 seconds at 720p.
Seedance 1.5 generates 4 to 12 second takes at up to 720p across 16:9, 9:16, and 1:1. That is enough range for social cutdowns and secondary shots inside a longer video.
- 4
Scenema uses a different model when the shot has to start from a text prompt.
Seedance 1.5 does not accept text-to-video input. If you do not have a reference image yet, use Seedance 2.0 or Kling 3.0 to generate the shot from a prompt directly.
- 5
Scenema uses a different model when the shot has to be delivered at 1080p or higher.
Seedance 1.5 caps at 720p. For a 1080p image-to-video pass, use Wan 2.6. For up to 4K, use Gemini Omni Flash.
FAQ
Frequently asked questions about Seedance 1.5
What is Seedance 1.5 on Scenema?+
Seedance 1.5 is ByteDance’s image-to-video model, exposed inside Scenema as an image-to-video shot generator in the long-form pipeline. Each generation is a shot of 4 to 12 seconds at up to 720p, driven by a reference frame, and Scenema packs those shots into full videos.
Can Seedance 1.5 do text to video on Scenema?+
No. Seedance 1.5 on Scenema is image-to-video only. Every generation requires a reference image as input. If a shot needs to start from a written prompt, Scenema uses a model that supports text to video, such as Seedance 2.0 or Kling 3.0.
What resolution and aspect ratios does Seedance 1.5 support on Scenema?+
Seedance 1.5 on Scenema outputs up to 720p in 16:9, 9:16, or 1:1. Pick the aspect ratio to match the finished video format.
How does Scenema make long-form videos if Seedance 1.5 only generates up to 12 seconds at a time?+
Scenema treats each Seedance 1.5 generation as one shot inside a scene. The pipeline plans the shot list, supplies the reference image for each shot, and assembles the results into scenes and full videos. Character consistency, voiceover, and music tracks run across every cut, so the finished piece plays as a single continuous video.
When does Scenema use Seedance 1.5 over Seedance 2.0 on Scenema?+
Scenema uses Seedance 1.5 when the shot is already anchored by a reference image and needs a standard-tier image-to-video pass. It uses Seedance 2.0 when the shot needs text or audio input, longer runtime up to 15 seconds, or joint audio-video generation.
Related
Other video models on Scenema
Veo 3.1
Google DeepMind- Google DeepMind’s flagship cinematic video model.
- 4, 6, or 8 second takes at up to 1080p, with audio generated in the same pass as the picture.
- Shot generator inside Scenema’s long-form pipeline.
Kling 3.0
Kuaishou- Kuaishou’s third-generation flagship video model.
- 4 to 12 second takes at 1080p, with native audio and stronger character consistency.
- Shot generator inside Scenema’s long-form pipeline.
Seedance 2.0
ByteDance- ByteDance’s multimodal video model with joint audio-video generation.
- Text, image, and audio inputs; up to 15 second takes, the longest on Scenema alongside MiniMax H3 and Vidu Q3 Turbo.
- Shot generator inside Scenema’s long-form pipeline.
Wan 3.0
Alibaba- Alibaba Tongyi Wanxiang’s current-generation Wan model, replacing Wan 2.6 on Scenema.
- Image-to-video with last-frame conditioning; 4 to 12 second takes at 720p.
- Image-anchored shot generator inside Scenema’s long-form pipeline.
MiniMax H3
MiniMax- MiniMax’s next-generation video model.
- Reference-to-video; 4 to 15 second takes at 768p.
- Complex motion and multi-entity consistency inside Scenema’s long-form pipeline.
Vidu Q3 Turbo
Shengshu- Shengshu’s Vidu Q3 Turbo, a start-and-end-frame image-to-video model.
- 1 to 15 second takes at 720p, driven by both a first frame and a last frame.
- Locks the shot to an exact ending composition for clean cut-to-cut choreography.
Gemini Omni Flash
Google- Google’s multimodal video model with native audio and 4K output.
- Image to video only; 4, 6, 8, or 10 second takes at up to 4K.
- Highest-resolution shot generator inside Scenema’s long-form pipeline.
LTX 2.3
Lightricks- Lightricks’ open video foundation model with Fast and Pro tiers on Scenema.
- Text, image, and audio inputs; 4 to 12 second takes at up to 1080p.
- Widest aspect-ratio range of any Scenema video model.
Start generating with Seedance 1.5 in Scenema
Seedance 1.5 is available on the Scenema free tier. Sign up and start your first explainer. Scenema uses it wherever it fits the style and the shot.
200 credits on signup, then weekly refills through your first month. No credit card required.