Models / Seedance / Image to video

Seedance image to video prompting guide

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

Prompt structure

action→camera→lighting change→audio→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

• fal image-to-video: prompt describes 'the desired motion and action'; image_url is the starting frame. source ↗
• Open by locking the first frame: 'The first frame is the uploaded image: keep its framing, camera angle, her face, hair, outfit … as they are.' Show force through what each action does, not adjectives ('show the force, don't name it'). community source ↗

What not to describe

• ModelArk treats first-frame, first+last-frame and multimodal-reference as separate scenarios: don't mix first/last-frame roles with reference images/videos/audio. 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

Same first frame, two models. Neither does both.  

Seedance hits harder and keeps her face. Kling moves her body more naturally. I went with force.  

Prompt tip: show the force, don't name it. Describe what each hit does, not how hard it is.  

Seedance 2.5 · 2 renders · ~$1.60 
Kling 3.0 · 1 render

Prompt 👇
One continuous 5-second shot. The first frame is the uploaded image: keep its framing, camera angle, her face, hair, outfit, the wooden mortar and the old wagashi shop as they are.
Camera: a phone held steady above and in front of her, looking down, the same framing as the first frame the whole time. The large wooden mortar fills the bottom of the frame and covers her below the waist throughout.
She is pounding mochi the traditional way, alone in the shop, and she hits it hard. Three heavy strikes in the five seconds. For each one she hauls the long straight wooden pole up with bo

Generated using Seedance 2.5 on @runwayml 
Upscaled with @topazlabs Astra 2

Prompt (I2V) : A mysterious surreal short video set inside a lush rainforest clearing that contains a fully functional office. Several people are calmly working inside the space as if nothing is unusual. The video should begin as an immersive exploration of the environment and slowly reveal that the entire scene is actually a miniature habitat.  Visual concept: A dense tropical jungle surrounds a mossy clearing beside still dark water. In the middle sits a carefully arranged office setup with a wooden desk, orange chair, green leather lounge chair, side stool, stereo equipment, desk lamp, laptop, papers, and a giant white wall clock partially overtaken by vines. The space feels humid, green, quiet, and impossibly serene. A few office workers are present, behaving naturally and professionally inside this bizarre

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
• seedrouter.ai/docs/seedance-2-0
• x.com/alessia_orbit/status/2108917079411683406