Seedance Camera logo

Seedance Camera

CommunityPopular
Emily2040
seedance-camera

This skill should be used when the user asks for camera movement, shot scale, lens feel, framing, one-take direction, dolly, pan, tilt, push-in, handheld, aerial, macro, or camera-transfer guidance for Seedance 2.0.

Overview

PublisherEmily2040
Repositoryseedance-2.0
Skill nameseedance-camera
Stars
7.4K
Forks
1.1K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Emily2040 on GitHub. Read the source before you install it.

Installation

Install the Seedance Camera AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Emily2040/seedance-2.0.git /tmp/seedance-2.0
mkdir -p .claude/skills
cp -r /tmp/seedance-2.0/skills/seedance-camera .claude/skills/seedance-camera
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Seedance Camera in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Seedance Camera on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Seedance Camera is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

seedance-camera

Before producing prompt text, a prompt-ready block, a rewrite, an example, or a compiled clip, load the Director's Read, classify the brief, and complete its canonical narrative or non-narrative record. Translate that record into visible or audible carriers and keep its internal labels out of final generation prose.

Use one clear camera idea per short clip unless the user asks for a multi-shot sequence. The best camera direction has a start frame, movement, speed, subject relationship, and endpoint. Avoid stacking moves that fight each other, such as drone rise, dolly-in, handheld shake, and orbit in the same five-second shot.

Load quick-ref for prompt assembly, cinematography-shot-language for professional shot contracts, directing-engine to derive the move from the scene's one intention so it reinforces light, performance, and sound instead of competing, and vocab/zh or vocab/ru when camera wording must be multilingual.

Intent

When a user asks about camera, they are really asking where the viewer's body stands and what the viewer is made to feel from there. Camera grammar is empathy mechanics: a push-in is leaning closer, a locked frame is holding your breath. Choose the move that puts the audience where the user's feeling lives.

Camera Contract

State: shot scale, angle, movement, speed, subject relationship, and endpoint. A prompt-ready camera phrase should be physically possible and tied to the subject's action.

NeedStrong phraseAvoid
Emotional realizationslow dolly-in from medium close-up to tight close-up as Character A lowers the envelopedramatic cinematic zoom
Product revealcontrolled slider move from silhouette to front three-quarter hero angle, ending on the labeldynamic product camera
Scalelow-angle crane up from boots to skyline, ending behind the character's shoulderepic wide moving shot
Instabilitysubtle handheld shoulder camera, small breathing sway, subject kept centeredshaky chaotic camera everywhere
Precision detaillocked macro shot, focus stays on the watch gears while the second hand clicks oncecool close-up details

Lens and Framing Anchors

Use lens anchors only when they improve direction: 24mm wide lens for spatial energy, 35mm natural street perspective, 50mm portrait compression, 85mm shallow close-up, or macro lens for material detail. Pair lens words with subject distance and motion; do not stack lens numbers as decoration.

Move Selection

Use locked-off shots for lip-sync, product identity, and delicate VFX. Use dolly-in for discovery or realization. Use tracking for travel, pursuit, and product motion. Use orbit only when the subject can remain clear from all sides. Use crane or drone for scale, arrival, or reveal. Use handheld only when realism matters more than precision.

Continuity Rules

For multi-character scenes, anchor the camera to named tags: camera holds Character A in foreground while Character B crosses behind. For I2V, preserve the image composition unless the user explicitly wants a reframing. For reference video, state whether @Video1 transfers camera movement, action rhythm, or blocking; do not let it transfer identity unless authorized.

For complex camera movement, a video reference often works better than a long verbal stack. Use @Video1 controls camera rhythm only; do not transfer performer, room, logo, or identity.

Conflict Rule

If the user gives several incompatible moves, choose one primary camera move and put the rest into optional variants. If the shot needs multiple beats, recommend splitting into separate clips or a time-segmented prompt.

Sequence State

When sequence state is present, inherit the observed camera phase, screen direction, current clip scope, continuity locks, exact reference tags, and reserved future beats before choosing a move. A continuation camera phrase must begin from the accepted source frame or observed end state; do not restart a pan, focus pull, or tracking move unless an intentional next shot declares the reset.

Output Contract

Return the selected camera phrase, why it fits the shot, conflicts removed, fragile anchors, endpoint, and a prompt-ready integrated sentence.

Frequently asked questions

What does the Seedance Camera AI skill do?

This skill should be used when the user asks for camera movement, shot scale, lens feel, framing, one-take direction, dolly, pan, tilt, push-in, handheld, aerial, macro, or camera-transfer guidance for Seedance 2.0.

Why use Seedance Camera on TypingMind?

Because you install it once and use it with any model. Seedance Camera is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Seedance Camera in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Emily2040/seedance-2.0/tree/main/skills/seedance-camera. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Seedance Camera?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Seedance Camera?

As many as you like. As long as a model supports skills, you can use Seedance Camera with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Seedance Camera AI skill free?

Yes. It is published on GitHub by Emily2040 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇