SeeDance 1.0 Pro
What is SeeDance 1.0 Pro?
SeeDance 1.0 Pro is ByteDance's first-generation Pro video model and the highest-quality variant in the 1.0 line. Two modes drive the result: text-to-video for fresh generation across six aspect ratios (1:1, 3:4, 4:3, 9:16, 16:9, 21:9), and first-and-last-frame interpolation for controlled hero shots between two reference images. Output is 720p, in 5 or 10 second clips. An integer seed parameter makes runs reproducible: re-sending the same prompt and frames with the same seed returns the same result, which is useful for A/B variants and locking in a clip you want to deliver. Use 1.0 Pro when 720p is enough and quality per clip matters more than throughput.
Key features of SeeDance 1.0 Pro
Four features cover what teams build with 1.0 Pro.
Text-to-video across six aspect ratios
1:1, 3:4, 4:3, 9:16, 16:9, and 21:9 in the prompt-only path. Each social channel has a native ratio that matches: 9:16 for Reels, 1:1 for feed, 16:9 for YouTube, 21:9 for ultra-wide hero placements.
First-and-last-frame interpolation
Pass first_frame_url (required) and optionally last_frame_url, and the model interpolates the motion between them. Aspect ratio is auto-detected from the input image, so the output matches the still you started from.
5 or 10 second clips at 720p
Two duration options on the same model. Pick 5 seconds for feed loops and short ads, 10 seconds for product reveals and longer beats.
Integer seed for reproducible runs
Pass a seed alongside the prompt and frames. Re-sending the same inputs and seed returns the same result. Useful for A/B variants, regression tests, and locking a clip you want to deliver.
Best for
Short ads with locked aspect ratios
Six aspect ratios match each social channel native. 9:16 for Reels, 1:1 for feed, 16:9 for YouTube.
Hero shots via interpolation
First-and-last-frame mode produces controlled motion between two known compositions. Useful for product reveals.
Quick concept videos
5 or 10 second clips at 720p are enough for client review and concept testing.
Storyboard animatics
Generate motion previews of static storyboard frames. Useful pre-production for film and animation.
Social-first content at low cost
Good when 720p is sufficient and the placement does not need a hero render.
A/B testing motion treatments
Same prompt with different aspect ratios shows how the same concept reads in vertical vs widescreen.
Use cases
Generate a short ad for a single platform by picking the right aspect ratio at the call site (9:16 for Reels, 1:1 for feed, 16:9 for YouTube) and running text-to-video at 5 seconds. Build a controlled product reveal between two locked compositions by passing first_frame_url and last_frame_url and letting the model handle the in-between motion. Lock in a chosen take for delivery by passing a seed alongside the prompt and reusing it on the final render. Run an A/B test on motion treatments by holding the prompt constant and varying only the aspect ratio across runs.
API examples
Call SeeDance 1.0 Pro from any language by POSTing to /v1/tasks. Full parameter docs live at docs.unifically.com/models/video/bytedance/seedance-1.0-pro.
curl -X POST https://api.unifically.com/v1/tasks \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "bytedance/seedance-1.0-pro",
"input": {
"prompt": "A person dancing in a vibrant street scene",
"mode": "text_to_video",
"aspect_ratio": "9:16",
"duration": 5
}
}'
Successful submission returns a task_id. Poll GET /v1/tasks/<task_id> or set a callback_url on the request to receive the finished result.
FAQs
People also ask
SeeDance 1.0 Pro is ByteDance's first-generation Pro video model. Two modes: text-to-video from a prompt across six aspect ratios, and first-and-last-frame interpolation between two reference images. Output is 720p, 5 or 10 seconds per clip, with an optional integer seed for reproducible runs.
You upload a starting frame (required) and optionally an ending frame. The model generates the in-between motion. Useful for hero shots where you know the open and close beats but want the middle handled. Aspect ratio is auto-detected from the input image.
Six in text-to-video mode (1:1, 3:4, 4:3, 9:16, 16:9, 21:9). First-and-last-frame mode uses the aspect of the input image.
5 or 10 seconds per call. For longer narratives, chain clips in post or move to SeeDance 1.5 Pro (which adds a 12-second option) or SeeDance 2.0.
No. SeeDance 1.0 Pro is video-only. Use SeeDance 2.0 if you need native audio in the same call.
Pick 1.0 Pro when output quality matters more than throughput and 720p is enough. Move to 1.0 Fast or 1.0 Mini for higher resolution (1080p) or multi-frame chaining; move to 1.5 Pro for 12-second clips and 1080p.
