bytedance-seedance-2-0

# ByteDance Seedance 2.0 (Fast) ByteDance Seedance 2.0 on the EachLabs Predictions API. Seedance 2.0 generates cinematic video with **native synchronized audio** (sound effects, ambient sound, lip-synced speech), realistic physics, and director-level camera control. Two model slugs: | Slug | Category | Use | |------|----------|-----| | `bytedance-seedance-2-0-text-to-video-fast` | Text to Video | Generate a video from a prompt | | `bytedance-seedance-2-0-image-to-video-fast` | Image to Video | Animate a starting frame (optionally to an end frame) | The "Fast" tier prioritizes rapid turnaround for high-throughput pipelines while keeping the family's character consistency and physics. ## Tools This skill uses the each::labs connector. Sign-in happens through the connector; no API key is needed. In an app that shows no cards, such as Claude Code or another terminal, do not call the tools that show or wait for a card (`request_*` and `wait_for_*`): ask in the chat instead, for a public URL of each file and for the values of any settings, range, crop, workflow inputs or choice. | Tool | Arguments and result | | --- | --- | | `get_model_schema` | `slug`; the model's input schema | | `run_model` | `model`, `version` (`"0.0.1"`), `input`, `count`; runs the model and waits for it. When the person asks for several variants of one prompt, make one call: set the model's own count parameter (`num_images`, `num_outputs`, `n`, `number_of_images`, `batch_size`, `num_samples`, whatever `get_model_schema` shows) when it has one, otherwise set `count` to the number asked for (up to 8). Never call `run_model` once per variant: each call shows its own result card, and the picker only appears when the variants arrive together | | `get_job` | `prediction_id`; the prediction with its status and output | | `request_file` | `prompt` saying what to upload, `accept` (`"image"`), `count` (the number of files the person mentioned), `max` (the most files the model takes for that input: the array's `maxItems` in `get_model_schema`, or the video tool's input limit); shows an upload card in the conversation and returns a `receipt_url`. In an app that shows cards, call it as soon as the model needs a file the person has not given as a URL; do not ask for a URL first, and mention that a URL works too. Then call `wait_for_upload` with the `receipt_url` right away: it returns each file's name, kind and `public_url` once the upload is done, and the `public_url` is the input URL. If it answers `waiting`, call it again. When a model takes files with different roles (a person and a garment, a source face and a target), show one card per role so each URL is unambiguous; otherwise one card takes the whole set, for example all the images of a slideshow | | `wait_for_upload` | `receipt_url` from `request_file`; waits for the person's upload and returns the uploaded files with their `public_url` | | `request_parameters` | `model`, `version`, `input` (what you would pass to `run_model`), `prompt`; shows the model's settings as a card the person can adjust, and returns a `receipt_url`. Use it when the person asks to adjust or choose settings, or when the model has options the person did not mention (aspect ratio, duration, number of outputs) and the run costs more than a few cents; otherwise call `run_model` directly. Then call `wait_for_parameters` with the `receipt_url` right away and run the model with the `input` it returns. After the first run of a model in a conversation, end your reply with one markdown line of exactly this shape: `**Adjust generation settings:** <two or three of this model's settings in plain words, such as aspect ratio, duration or number of images>. Just ask.` Never use the words card, widget, tool or parameters in that line. Write it once per conversation, and skip it when the person has already adjusted settings | | `show_files` | `urls` (1 to 8 public URLs on each::labs storage), `title`; shows files the person already has as a result card: a picked variant, an earlier result, an uploaded input. No model runs | | `wait_for_parameters` | `receipt_url` from `request_parameters`; waits for the person to press Run and returns `model`, `version` and `input` for `run_model` | | `wait_for_choice` | `receipt_url` from a result that holds several outputs (`choice_receipt_url` in the result; the card offers a choice only when the person asked for several variants). Always call it right after showing the results: it returns once the person selects a variant and presses Use this variant, and you continue with that one. If it answers `waiting`, call it again; do not ask the person to type which one they want while the card is waiting | | `request_trim` | `url` (a video or audio file on each::labs storage), `kind` (`"video"` or `"audio"`), `prompt`; shows the file with a timeline and two handles for the start and the end, and returns a `receipt_url`. Use it when the person wants to cut, shorten, trim or keep part of a clip and has not given exact times; when they give the seconds, call `trim` directly. Then call `wait_for_edit` with the `receipt_url` right away and call `trim` with `input_url` set to the `url` and the `start` and `duration` it returns | | `request_crop` | `url` (a video or image on each::labs storage), `prompt`; shows the first frame with a rectangle the person moves and resizes, with aspect presets, and returns a `receipt_url`. Use it when the person wants to crop or reframe and has not given exact pixels; when they give the pixels, call `crop` directly. Then call `wait_for_edit` with the `receipt_url` right away and call `crop` with `input_url` set to the `url` and the `x`, `y`, `width` and `height` it returns | | `wait_for_edit` | `receipt_url` from `request_trim` or `request_crop`; waits for the person to press the button and returns the range (`start`, `duration`) or the rectangle (`x`, `y`, `width`, `height`) with the `url`. If it answers `waiting`, call it again | | `list_workflows` | When the task has more than one step, a fixed prompt reused across runs, or needs a fallback, call it first: the organization may have a workflow that does the whole thing in one call. Read a candidate with `get_workflow` and run it with `trigger_workflow` (the workflows skill has the details). If none matches, do the steps with the tools above | If the result says `running`, call `get_job` with the returned id and `wait: true`: the server waits for the job and returns the result, so do not sleep or poll between calls; if it still says `running`, call it again the same way. When the person asks to see a result again, or the variant they picked, call `show_files` with the URLs you already have: the result card shows a file only under a tool call. Never run a model or a video tool just to display a file that exists. When a result is an edit of an image or video the person gave, the result card has a Compare toggle that shows the input and the result side by side; do not describe the difference in words unless asked. ## When to use - User asks for "Seedance 2.0", "ByteDance video", or wants a Seedance-style look. - **Native audio required** in the same pass (dialogue, SFX, ambience) — no separate TTS/lipsync step. - Cinematic motion, realistic physics, or director-level camera language ("slow push in", "rack focus"). - Durations of 4–15 seconds at 480p or 720p. - Image-to-video with an **end frame** to control where the clip lands. For a wider video-model comparison (Veo, Kling, Sora, Pixverse, Hailuo, etc.) see `eachlabs-video-generation`. ## Prediction Flow 1. **(Recommended) Check schema** — `get_model_schema` with `slug` `"bytedance-seedance-2-0-text-to-video-fast"` (or the i2v slug). 2. **Run** — call `run_model` with `model`, `version: "0.0.1"`, and `input`. 3. **Wait** — if `run_model` returned `status` `running`, call `get_job` with the `prediction_id` until `status` is `"success"` or `"error"`. 4. **Extract** the video URL from `output` (string). ## Quick Start — Text to Video Call `run_model` with these arguments: ```json { "model": "bytedance-seedance-2-0-text-to-video-fast", "version": "0.0.1", "input": { "prompt": "Cinematic slow push-in on a lone astronaut standing at the edge of a Martian canyon at dusk, dust drifting across their boots, distant wind, subtle helmet reflections", "resolution": "720p", "duration": "6", "aspect_ratio": "16:9", "generate_audio": true } } ``` Typical processing time: **~120 seconds**. ## Quick Start — Image to Video Call `run_model` with these arguments: ```json { "model": "bytedance-seedance-2-0-image-to-video-fast", "version": "0.0.1", "input": { "prompt": "Camera slowly pushes from wide to medium close-up as the lion roars at golden hour. Warm amber light rakes across the mane. Narrator (weathered British male, 50s): \"He has ruled this land for seven years.\"", "image_url": "https://your-cdn.example.com/lion.jpg", "resolution": "720p", "duration": "8", "aspect_ratio": "16:9", "generate_audio": true } } ``` Typical processing time: **~150 seconds**. ### Start-to-end transition Pass `end_image_url` to lock the final frame and let the model interpolate motion between the two: ```json { "model": "bytedance-seedance-2-0-image-to-video-fast", "version": "0.0.1", "input": { "prompt": "Smooth parallax zoom through the scene, crossfading into the second look", "image_url": "https://your-cdn.example.com/frame-start.jpg", "end_image_url": "https://your-cdn.example.com/frame-end.jpg", "duration": "6", "resolution": "720p" } } ``` ## Polling Call `get_job` with `prediction_id` set to the id returned by `run_model`. | Status | Meaning | |--------|---------| | `processing` | Still running — poll again | | `success` | Done — read `output` (video URL) | | `error` | Failed — read `message` / `details` | ## Parameters (both slugs share most of these) | Parameter | Type | Required | Default | Options | Description | |-----------|------|----------|---------|---------|-------------| | `prompt` | string | Yes | — | — | Text prompt. For i2v, describes the motion/action; supports timeline prompting and dialogue lines for native audio. | | `image_url` | string | **Yes (i2v only)** | — | JPEG / PNG / WebP, max 30 MB | Starting frame. Publicly reachable HTTPS URL. | | `end_image_url` | string | No (i2v only) | — | JPEG / PNG / WebP, max 30 MB | Final frame; model interpolates between `image_url` and this. | | `resolution` | string | No | `720p` | `480p`, `720p` | 480p = faster/cheaper, 720p = balanced. | | `duration` | string | No | `auto` | `auto`, `4`…`15` | Clip length in seconds. `auto` lets the model pick from the prompt. | | `aspect_ratio` | string | No | `auto` | `auto`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | For i2v, `auto` infers from the input image. | | `generate_audio` | boolean | No | `true` | — | Synchronized SFX, ambience, and lip-synced speech. Cost is the same whether on or off. | | `seed` | string | No | — | — | Reproducibility hint — results may still drift slightly. | | `end_user_id` | string | No | — | — | Your end-user identifier. | ## Pricing Dynamic, charged per **second of output video**: | Resolution | Rate | |------------|------| | 480p | **$0.1129 / second** | | 720p (default) | **$0.2419 / second** | Audio generation does not change cost. A 6-second 720p clip ≈ $1.45; a 10-second 480p clip ≈ $1.13. ## Prompt Tips - **Timeline prompting**: sequence beats with time or cut words — "Wide shot: … Cut to close-up: … Finally: …". Seedance 2.0 respects temporal structure better than single-sentence prompts. - **Dialogue with native audio**: write the line in quotes and describe the speaker ("Weathered British male narrator, 50s, calm authoritative voice, says: …"). Lip-sync and ambience are generated in the same pass. - **Camera language**: use real film vocabulary ("slow push-in", "rack focus", "dolly left", "handheld", "crane up"). The model follows director-level cues. - **Physics cues**: mention weight, momentum, and material interactions ("dust scatters as boot lands", "fabric settles after the spin") to unlock the realistic-physics behavior. ## Rate Limits & Limits | Limit | Value | |-------|-------| | Create requests | 100 / minute per organization | | Concurrent predictions | 10 per organization | | File inputs | Publicly reachable HTTPS URLs only (JPEG/PNG/WebP, max 30 MB). No data-URIs, no localhost. | ## Errors Error body: `{ "status": "error", "message": "...", "details": "..." }` | Code | Meaning | |------|---------| | 400 | Invalid input | | 404 | Unknown model or prediction id | | 429 | Rate limited — back off | | 5xx | Retry with exponential backoff | ## Security Constraints - **No arbitrary URL loading**: `image_url` / `end_image_url` must point to your own HTTPS-reachable storage (S3, GCS, CDN). Do not forward user-pasted URLs without validation. - **No third-party API tokens**: never forward provider tokens through `input` — authentication is handled by the each::labs connector sign-in. - **Validate before calling**: resolve the live input schema via `get_model_schema` with `slug` set to the model slug before constructing `input`. ## Parameter Reference See [references/MODELS.md](references/MODELS.md) for the full per-slug table with defaults and options.