Seedance prompt generator

The order Seedance 2.5 reads

ByteDance’s Seedance 2.5 tutorial gives one basic formula: subject + action or event + scene and environment + visual style + camera movement or shot cuts + sound. Parts you don’t need can be left out. The generator keeps that order. With the sample scene used across this site, the output looks like this:

A young woman in a red raincoat stops and looks up as the rain starts in a neon-lit Tokyo side street at night.
Cinematic 35mm film style, soft neon lighting, quiet, nostalgic mood.
Push in.
0-3s: Wide shot, she walks toward the camera under the neon signs.
3-6s: Close-up, raindrops land on her face and she smiles.
Sound: <rain on the pavement, distant traffic> The woman says in English {It finally came.}
No subtitles.
No BGM, only ambient and action sounds.

Timestamps in 2.5, shot numbers in 2.0

Seedance 2.5 follows whole-second timestamps, written as ranges like “0-3s: … 3-7s: …” or “[1s-4s] …”, or as points in time like “at 5s, fast whip-pan left”. Keep the ranges continuous: the guide warns against gaps such as “0-3s … 5-6s”, and against using timestamps to control frequency (“shakes head 3 times per second”).

ByteDance’s Chinese guide says Seedance 2.0 responds to shot numbers, not timestamps, and the English guide adds that its control over exact timing is unstable: forcing durations can produce abnormal results. It asks for “Shot 1 / Shot 2 / Shot 3” in the order events happen, with one camera move per shot, and puts style after the camera instructions. Switch the model to Seedance 2.0 and the generator writes it that way:

A young woman in a red raincoat stops and looks up as the rain starts in a neon-lit Tokyo side street at night.
Soft neon lighting, quiet, nostalgic mood.
Push in.
Shot 1: Wide shot, she walks toward the camera under the neon signs.
Shot 2: Close-up, raindrops land on her face and she smiles.
Cinematic 35mm film style.
Sound: <rain on the pavement, distant traffic> The woman says in English {It finally came.}
Keep no subtitles, no background music.

Sound, dialogue and subtitles

• Round brackets ( ) mark music, angle brackets < > sound effects, curly brackets { } dialogue and 【 】 on-screen subtitles.
• For dialogue in any language other than Chinese, name the language first: says in English {…}. Keep each line in one language. The generator adds the language you pick next to the line.
• ByteDance’s guide lists subtitles and audio as what a “no” instruction works for in Seedance 2.5: “No subtitles”, “No BGM, only ambient and action sounds”, “No dialogue”. It also notes that neither version fully guarantees a clip without subtitles.
• For everything else, describe what you want to see instead of what you don’t.

Camera terms Seedance understands

The guide lists terms you can write directly: shot sizes from extreme wide shot to extreme close-up; moves such as push in, pull out, pan, truck, follow, orbit, dive, pull back, tilt up and handheld shake; angles such as low angle, top-down and first-person POV; and popular techniques such as one-take, Hitchcock zoom, aerial, FPV, bullet time and speed ramp. For niche jargon, write the term followed by a plain description of what the camera does.

Reference images, videos and audio

Number each reference by upload order within its type, @Image 1, @Video 1, @Audio 1, and say what it contributes (look, motion, voice, camera move) and what not to take from it. With several characters, map each one explicitly instead of relying on names written inside the image. Resellers use their own tags: fal writes @Image1 and Replicate [Image1].

Seedance 2.5 vs 2.0

Related tools

• Seedance 2.5 price per secondSeedance 2.5 price per second: about $0.103 at 480p, $0.231 at 720p and $0.569 at 1080p on BytePlus. Compare fal, Replicate, Runware, WaveSpeed, OpenRouter.
• Kling prompt generatorFree Kling prompt generator. Writes Kling 3.0 prompts in Kling’s own order and splits them into up to six shots with the official “shot n, m, words;” syntax.
• Wan 3.0 prompt generatorBuild Wan 3.0 prompts in Alibaba’s recommended order: overall description, timed shots, dialogue, sound, style and a negative list. Free, no sign-up.
• MiniMax H3 prompt generatorWrite MiniMax H3 prompts the way the official cookbook lays them out: one core sentence, a shot-by-shot timeline and exclusions at the end. Works for Hailuo AI.