seedance-2-0
Direct ByteDance Dreamina Seedance 2.0 Standard, Fast, and Mini video production across BytePlus ModelArk and verified gateways. Use for text/image/reference-to-video, native synchronized audio and dialogue, multimodal image-video-audio reference, first/last-frame animation, video editing or extension, model/gateway selection, prompt construction, async task handling, failure recovery, QA, and rights-safe production.
npx skills add calesthio/generative-media-skills --skill seedance-2-0 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Direct Seedance 2.0 production acts as a provider- and model-family-specific operating guide for creating 4–15 second shots with synchronized media (image, video, audio) and multimodal references. It instructs users to establish the exact gateway contract before writing a request and to select among BytePlus ModelArk variants (Seedance 2.0, Seedance 2.0 Fast, Seedance 2.0 Mini) according to quality, latency, and cost needs. It emphasizes using official endpoints, top-level JSON payloads, and specific media roles (first_frame, reference_image, reference_video, reference_audio) when building content.
How it works
The guide prescribes: establish gateway contracts and use the official APIs and model IDs for Seedance 2.0 family; choose the appropriate modelArk ID from a documented table; construct a direct ModelArk request envelope with fields like model, content, resolution, ratio, duration, generate_audio, watermark, return_last_frame, callback_url, execution_expires_after, safety_identifier, and priority. It requires using ordered text/image/video/audio items with roles to define first/last/reference behavior, validates media via ffprobe-like checks, and assigns one job per reference using an asset ledger. It details how to write prompts as executable direction, with steps for defining subjects, binding references, describing settings, actions, and camera moves, and outlines mode-specific directions for text-to-video, first/last frame, multimodal reference, video editing, and extension tasks. It provides example payload structures for the content array and strict guidance for media validation and asset management.
When to use it
Use when the shot benefits from synchronized generation across media types, needs reference materials for subject/style/layout, or requires a short, self-contained sequence (4–15 seconds) with first-frame or first-and-last-frame transitions, or a multimodal edit where an element from one asset modifies another source video. It also governs decisions about model Ark variants and gateway endpoints before prompting.
What it can touch
Touchpoints include: BytePlus ModelArk endpoints for creation and retrieval, model IDs such as dreamina-seedance-2-0-260128 and fast/mini variants, and gateway contracts (BytePlus ModelArk, fal, Replicate) with their respective endpoint patterns and response structures. It instructs constructing the content[] payload and media validation steps before submission.
Caveats
Notes include that Seedance 2.0 endpoints do not support frames, seed, or camera_fixed for this version; several gateway-specific constraints exist (aspect_ratio, duration as enum or integer, and the presence of relationships between reference assets). It warns to verify live model card and activation status, and to fetch prices and limits at preflight rather than hardcoding values. It also cautions about reproducibility being gateway-specific and to follow the active endpoint’s schema for media labeling and prompts.
# Direct Seedance 2.0 production Treat this as a provider- and model-family-specific operating guide, not a generic video-prompt recipe. Establish the exact gateway contract before writing a request. “Seedance 2.0” does not imply one portable model ID or schema. Evidence labels used here: - **Documented** — stated in ByteDance/BytePlus or gateway documentation, verified 2026-07-09. - **Production
What does the seedance-2-0 skill do?
Direct ByteDance Dreamina Seedance 2.0 Standard, Fast, and Mini video production across BytePlus ModelArk and verified gateways. Use for text/image/reference-to-video, native synchronized audio and dialogue, multimodal image-video-audio reference, first/last-frame animation, video editing or extension, model/gateway selection, prompt construction, async task handling, failure recovery, QA, and rights-safe production.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill seedance-2-0 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.