Models / Seedance / Text to video

Seedance text to video prompting guide

How to prompt Seedance in text-to-video mode. Every point links its source; community tips are marked. Your agent gets the same guide through the Atlas MCP (get_guide).

Prompt structure

subject→action→scene→lighting color→camera→style→quality→constraints

• Formula: precise subject + action details + scene/environment + lighting & colour tone + camera movement + visual style + image quality + constraints. source ↗
• Open with a one-paragraph summary (duration, aspect, one continuous shot, what the first frame looks like and where the last frame lands), then lock subject/world with numbers (8 metres, 85-200mm, golden-hour side sun), then timestamped blocks. community source ↗
• Time-segmented prompts for 10 s+: '0–3s: … 3–6s: … 6–10s: … 10–15s: …'. community source ↗

What the text should describe

• Describe the full scene: subject, action, environment, light/colour, one camera move, style, quality, constraints. source ↗

What not to describe

• Don't stack several camera moves in one shot. source ↗

Camera vocabulary

• Standard terms work (medium shot, close-up, slow push-in, smooth lateral tracking, fixed shot). Use ONE camera movement per shot; combining push, pull, pan and move raises instability. source ↗

Responds well to

• Name body parts with range, speed and force (slowly raise a hand, quickly turn the head); prefer slow, continuous movement; show emotion through physical detail, not 'very sad'. source ↗

Duration and limits

• fal Seedance 2.0: duration 4–15 s or 'auto'; 480p/720p/1080p/4k; aspect auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; generate_audio default true. source ↗

Multi-shot

• Complex clips: timeline storyboard 'Shot 1 / Shot 2 / Shot 3', each with who + where + doing what + camera + audio; don't force per-shot durations. source ↗

Avoid and failure modes

• Constraint phrases: 'keep it subtitle-free', 'avoid generating any text or subtitles', 'do not generate a logo', 'do not generate a watermark'. Subtitles cannot be suppressed 100%. source ↗
• Keep dialogue in one language; avoid mixing Chinese and English except proper nouns. source ↗
• Prefer positive mechanisms over long negative lists ('enters through the rear doorway' not 'do not teleport'); keep a few targeted exclusions for observed failures and place each rule next to the event it governs. community source ↗
• Don't ask for 'static camera' and 'orbit' in the same segment; don't overload 4–5 s with many scenes. community source ↗

Negative prompt

Not supported; describe what you want instead. source ↗

Real prompts, credited

They thought she was defenseless, but the dragon changed their minds.

Seedance 2.5 on @makeugc 

Prompt:

Vertical 9:16, 30-second continuous cinematic scene in a dark fantasy forest camp. The first frame is already in motion: a calm silver-haired woman walks into a ring of armed dark elf soldiers while a furious elf archer raises her bow at her. The tension builds through alternating close-ups of cold calm versus barely held rage, with short spoken dialogue, and ends with a giant white dragon rising behind the woman while the archer lowers her bow.

REFERENCES (use these images as the exact look of each character, face, hair, outfit, props, in every shot)
image1 = the woman. image2 = the archer. image3 = the guard. image4 = the dragon.

MAIN SUBJECTS

Woman (image1, the calm one): age about 27, warm tan skin with light freckles. Very long, perfectly straight PLATINUM SILVER-GREY hair p

Seedance 2.5 Prompt:
A 30-second photorealistic science-fiction short. Begin with an intimate conversation above a living city. Natural skin and fabric, cool dusk-blue sky against warm city lights. No subtitles, narration or music. Natural English dialogue with accurate lip sync.

The young man has short dark hair; the young woman has dark hair tied low. They wear fitted dark contemporary jackets and ordinary trousers. Keep their faces, hair, age, voices and proportions unchanged. Man screen-left, woman screen-right in every shared view. They sit facing outward on the skyscraper edge, shoulders lightly touching, lower legs dangling. Her right hand rests on the ledge beside her hip. Keep the apparent rooftop reality complete until 21s: no uniforms, ship fittings, interface or digital artifacts.

Shot 1, 0-3s. Rear-right three-quarter wide, slowly approaching. Hold both the darkening sky a

Next

Sources

• docs.byteplus.com/en/docs/modelark/seedance-2-0-prompt-guide
• docs.dev.runwayml.com/api/
• fal.ai/models/bytedance/seedance-2.0/image-to-video/api
• github.com/dexhunter/seedance2-skill/blob/main/SKILL.md
• github.com/mattvideoproductions/MVP-Prompts/blob/main/seedance25_prompting_guide.txt