Examples

One-take handheld gimbal tracking shot. The camera slowly pushes in through a gap in a heavy red curtain and enters a warm-toned backstage dressing room. A young female singer, with her back to the camera, is adjusting her earpiece as a staff member reminds her it's time to go on. She turns toward the camera and starts singing citypop. The camera pulls back and tracks her as she passes through the curtain into a dim backstage corridor, interacting naturally with her dancers along the way; one staff member hands her a microphone. She and the dancers then step onto the stage, and the camera arcs around to the back, gradually revealing the red-and-black stage design, LED screens, spotlights, haze, and reflective floor. The camera finally pulls out to a wide shot of the arena, showing the packed audience, light boards, glow sticks, and cheering crowd, capturing the youthful, free-spirited climax of the concert.

Edit @Video 1. Keep the characters, actions, and visual style unchanged. Adjust only the camera movement. A 15-second segmented camera plan: 0–4s, a micro-FPV move skims tightly past the pan, then follows the popping toast and whip-pans to the coffee; 4–7s, push in and track laterally along the rim of the pan, following the fried egg as it flips up and lands back in place; 7–11s, rapidly rise to a top-down view, then descend at a steady pace, sweeping across the plate and keys; 11–15s, use a handheld close-up to follow the hands with a fast lateral whip, then push in on the breakfast and pull back to a medium two-shot. Keep the entire sequence smooth, continuous, and stable.

Extend the video. Continue from the visuals and subjects in @Video 1 and generate another 30-second clip, keeping the character subjects, scene, visual style, and sound effects consistent. The little boy runs along the train carriage holding a soccer ball. When the subway stops, the side door opens and he immediately dashes out, with the male lead chasing after him. The two run across the platform and out onto the street, startling passersby and vehicles along the way. The male lead finally catches up and grabs him. The boy looks up, aggrieved. The male lead's anger slowly fades; he pats the boy's head and shows a helpless smile.

Example result

About Seedance 2.5

Seedance 2.5 (seedance-2.5) generates video from 4 to 15 seconds at 480p through 1080p. It is offered in Global and CN regions and is submitted through POST /v1/generations.

Besides ordinary reference images, it accepts first-frame and last-frame images. Pick it when you want to control which picture the video starts from and where it ends.

Key features

First and last frame control
Set first_frame_image_url and last_frame_image_url to the image URLs for the opening and closing frames.
Reference images
Pass reference image URLs in reference_images to keep a subject or scene consistent with your source material.
480p to 1080p resolution
resolution accepts 480p, 720p (default) and 1080p.
4 to 15 seconds
duration accepts 4 to 15 seconds, with a default of 5.
Audio on by default
generate_audio defaults to true. Aspect ratio options are 21:9, 16:9 (default), 4:3, 1:1, 3:4 and 9:16.

Use cases

Transitions and transformations from a first to a last frame
Animating a still key visual
Before-and-after product showcases
Social media shorts
Ad creatives and campaign variations

Get started in four steps

Create an API key in the console.
Pick the model and review its parameters in the API tab.
Fill in the parameters and check the cost with the quote endpoint.
Submit the request, then poll the task or receive a webhook for the result.

Writing prompts

[Opening frame] + [Action or change] + [Closing frame] + [Camera movement] + [Lighting and style]

With first and last frames, focus the prompt on the action and camera movement between them.
Keep the subject and composition of both frames similar for a smoother transition.
Describe one shot at a time and keep the action achievable within the duration.

Example prompts

A cinematic product reveal
A flower bud slowly opening into full bloom, static close-up, soft backlight
The camera pushes slowly into an empty room as furniture appears piece by piece, ending on a furnished living room

FAQ

Can I send both a first and a last frame?⌄

Yes. first_frame_image_url and last_frame_image_url are both optional; send either or both.

Can I send has_video_input?⌄

No. has_video_input is derived by the server and must not be supplied by clients.

How is it billed?⌄

The Price tab lists every tier. Call POST /v1/quote first and send exactly the same parameters when creating the task. API calls only spend purchased permanent credit packs and admin-adjusted credits.

Is the request synchronous?⌄

No. Creating a task returns a task_id; poll GET /v1/tasks/{task_id} or receive a webhook when it finishes.

Model	Capabilities	Resolution and duration	From
Seedance 2	Audio to video · First frame to video · First and last frame to video · Image to video · Reference to video · Text to video · Video to video	480p / 720p / 1080p / 4K · 4–15s	Output 474 API Credits / 1M tokens≈ $5.21
Seedance 2 Fast	Text to video · Image to video · First frame to video · First and last frame to video · Reference to video · Video to video · Audio to video	480p / 720p · 4–15s	Output 651 API Credits / 1M tokens≈ $7.15
Seedance 2 Mini	Audio to video · First frame to video · First and last frame to video · Image to video · Reference to video · Text to video · Video to video	480p / 720p · 4–15s	Output 414 API Credits / 1M tokens≈ $4.55

ByteDance / Seedance 2.5

Examples

Example result

About Seedance 2.5

Key features

First and last frame control

Reference images

480p to 1080p resolution

4 to 15 seconds

Audio on by default

Use cases

Get started in four steps

Writing prompts

Example prompts

FAQ

Other models from this provider