Image-to-Video Generation up to 1080p with Seedance 2.0
ByteDance's Seedance 2.0 Image-to-Video animates a first-frame image — with optional last frame for controlled transitions — into cinematic video with synchronized audio. Supports resolutions up to 1080p, making it ideal for production-quality image-to-video at scale.
What makes Seedance 2 Image-to-Video different
Animate any image at up to 1080p
Upload a still and Seedance 2.0 brings it to life for 4 to 15 seconds — and unlike the newer Seedance 2.5, it can render the result at full-HD 1080p via super-resolution. That makes 2.0 the Seedance pick when an animated product shot or key art has to hold up at full screen.
First and last frame control
Set just a first frame and let the model decide where the motion goes, or add a last frame to lock the ending — the video transitions from your opening image to your closing one. Match cuts, transformations, and loops become directable instead of lucky.
Synchronized audio, on by default
Like every Seedance 2.0 mode, image-to-video generates sound with the picture: ambient audio, effects, and music that match the scene you animated. Turn it off with one toggle for silent footage — the per-second price is the same.
Chain it on a Scenetra board
Generate a still with an image model, wire it straight into a Seedance 2.0 Image to Video node, then feed the result into an upscaler or sequencer — all on one canvas. Because pricing is per second, you can draft the motion at 480p and re-run the keeper at 1080p without touching the rest of the pipeline.
Playground
A timelapse of a flower blooming in a sunlit meadow, cinematic quality
Drop images or click to upload
Try Seedance 2 Image-to-Video in Scenetra
Open PlaygroundParameters
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | text | Optional prompt describing the motion and scene. Recommended for best results. | — |
| First Frame* | image upload | The source image to animate (starting frame). Required. | — |
| Last Frame | image upload | Optional ending frame for controlled first-to-last transitions. | — |
| Duration | select | Length of the generated video in seconds.4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15 | 5 |
| Resolution | select | Output video resolution. 1080p is produced via super-resolution.480p · 720p · 1080p | 720p |
| Aspect Ratio | select | Video aspect ratio (defaults to matching the first frame).auto · 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 | auto |
| Generate Audio | select | Generate synchronized audio with the video.false · true | true |
Pricing
From $0.11 per second
Pay per generation — only pay for what you use.
480p
$0.11/s
per second
720p
$0.24/s
per second
1080p
$0.54/s
per second
What a video costs
| Duration | 480p | 720p | 1080p |
|---|---|---|---|
| 5 seconds | $0.55 | $1.22 | $2.75 |
| 10 seconds | $2.43 | $5.47 |
Use cases
Product & e-commerce
- Animate product photos
- 1080p hero clips from stills
- Listing videos
- Seasonal variants
Portraits & avatars
- Talking portrait clips
- Character intros
- Profile animations
- Style reveals
Storyboards & film
- Animate concept art
- Previz from key frames
- First-to-last match cuts
- Establishing shots from stills
Social content
- Bring photos to life
- Vertical 9:16 stories
- Before/after transitions
- Sound-on hooks
Related models
Seedance 2.5 Image-to-Video
Animate any image into a cinematic video up to 30 seconds with Seedance 2.5 by ByteDance. Start from a first-frame image, optionally set a last frame to control the ending, and get synchronized audio by default. Output preserves your image's aspect ratio.
View model →Seedance 2 Mini Image-to-Video
Seedance 2 Mini Image-to-Video animates a first-frame image — with optional last frame for controlled transitions — into a cinematic clip with synchronized audio. ByteDance's fast, budget-friendly tier for turning stills into motion at scale.
View model →Veo 3.1
Google's premier video generation model supporting text-to-video, image-to-video, and first-last-frame video creation. Veo 3.1 delivers up to 4K resolution with native audio synthesis, making it one of the most versatile video models available.
View model →Kling 3.0 Pro
Kuaishou's flagship video generation model delivering stunning visual fidelity. Kling 3.0 Pro supports text-to-video, image-to-video with start/end frames, element references for character consistency, and native audio generation.
View model →Frequently asked questions
What is Seedance 2.0 Image to Video?+
It's the image-to-video mode of ByteDance's Seedance 2.0 model: upload an image and it becomes the first frame of a generated video of 4 to 15 seconds, at up to 1080p, with synchronized audio created alongside the picture. On Scenetra it runs as a node in the visual workflow editor — no API key needed.
Can I use Seedance 2.0 image to video online for free?+
You can try it free online: Scenetra runs in the browser (it works anywhere, including the USA), and new accounts get free welcome credits plus a 7-day trial that covers your first generations. After that it's pay-per-generation — about $1.22 for a 5-second 720p clip — with no subscription required and nothing to cancel.
How does first and last frame control work?+
The required image sets the video's first frame. Optionally add a second image as the last frame, and the model generates the motion that connects them — useful for transformations, camera moves that land on a specific composition, and seamless loops (use the same image for both ends).
How much does Seedance 2.0 image to video cost?+
About $0.11 per second at 480p, $0.24 per second at 720p, and $0.54 per second at 1080p, audio included. A 5-second 720p animation is about $1.22; the same clip at 1080p is about $2.75. You pay per generation from your credit balance.
Does the video keep my image's aspect ratio?+
By default, yes — aspect ratio is set to auto, which matches the first frame, so a 9:16 portrait becomes a 9:16 video. You can also override it and pick a specific ratio from 21:9 to 9:16 if you want a different frame than your source image.
When should I use Image to Video vs Text to Video or Reference to Video?+
Use Image to Video when the exact first frame matters — a product shot, a character design, generated art you want to keep. Use Text to Video when you're starting from an idea and want the model to invent the visuals. Use Reference to Video when you need to guide the generation with multiple assets — up to 9 images, 3 videos, and 3 audio tracks — rather than pin down a single starting frame. All three cost the same per second.
Start creating with Seedance 2 Image-to-Video
Use Seedance 2 Image-to-Video alongside 50+ other AI models in Scenetra's visual workflow editor. No setup required.
Get Started Free