Werydance 2.0 video generator (almighty-ready)
Generate Werydance 2.0 videos on WeryAI with one skill for text-to-video, image-to-video, first-frame/last-frame transition video, multi-image storyboard video, and almighty mixed-reference video generation.
Animate and transform scenes from single images, storyboard frames, or mixed references while keeping subject and motion continuity.
Dependencies: scripts/video_gen.js at the skill package root (alongside SKILL.md) + WERYAI_API_KEY + Node.js 18+. No other Cursor skills are required.
- text-only generation
- single-image animation
- multi-image storyboard generation
- first-frame/last-frame compatibility aliases
- almighty mixed references (
images + videos + audios + prompt)
Runtime secret: only WERYAI_API_KEY.
Core upgrade
This skill now supports four input modalities for richer control:
- Image reference: composition, character, and detail lock
- Video reference: camera language, action rhythm, effect imitation
- Audio reference: mood and timing guidance
- Text prompt: intent and constraints
Smart routing policy:
- If payload includes
videos or audios, route to POST /v1/generation/almighty-reference-to-video.
- Otherwise keep legacy routing (
text-to-video, image-to-video, multi-image-to-video).
Prerequisites
WERYAI_API_KEY must be set.
- Node.js 18+.
- Prefer public
https URLs for media.
- Local files are supported and auto-uploaded by this skill via
POST /v1/generation/upload-file.
export WERYAI_API_KEY="your_api_key_here"
Quick checks
node scripts/video_gen.js models --mode text_to_video
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"A glowing koi swims through ink clouds","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}' --dry-run
Modes and input shapes
| Mode |
Trigger |
API route |
Key fields |
| Text |
no media refs |
/v1/generation/text-to-video |
prompt, duration, optional aspect_ratio, resolution, generate_audio |
| Single image |
image only |
/v1/generation/image-to-video |
image, prompt, plus common fields |
| Multi image |
images only |
/v1/generation/multi-image-to-video |
images, prompt, plus common fields |
| Almighty |
has videos or audios |
/v1/generation/almighty-reference-to-video |
images, videos, audios, prompt, video_number, plus common fields |
Compatibility aliases still supported:
first_frame + last_frame -> normalized to ordered images
image + last_image -> normalized to ordered images
Almighty constraints
Almighty validations in this skill:
prompt max 500 chars
images <= 9
videos <= 3
audios <= 3
- mixed file total (
images + videos + audios) <= 12
- at least one of
images or videos
duration must be 5-15 seconds
video_number must be 1-4
Notes:
- Backend enforces media-duration constraints for reference clips.
- Per current OpenAPI contract, almighty duration floor is 5s.
Local upload behavior
Supported local files before generation submit:
- Images:
jpg/jpeg/png/webp/gif, max 10MB
- Videos:
mp4/mov, max 50MB
- Audios:
mp3/wav, max 50MB
Upload endpoint used by this skill:
- Shot scale, angle, and lens feel.
- Camera movement or a clear lock-off choice.
- Lighting direction, material response, and overall mood.
- Subject motion paced to the selected
duration.
- One clear visual payoff in the final shot.
- Output framing such as
9:16 vertical when using the default aspect ratio.
- Audio (default-on): Add a labeled
Audio: block (ambience, layered SFX, subtle foley—generic, non-copyrighted) even if the user never mentioned sound. JSON generate_audio defaults to true for models that support audio; use false and omit Audio: only when the user explicitly wants silent output.
Dry-run behavior:
--dry-run never uploads local files
- output includes
uploadPreview to show which local paths would be uploaded
Prompt workflow (mandatory)
Before paid submit, expand brief into production prompt:
- Decide mode.
- Map each media to explicit role.
- Build 2-4 timeline beats by duration.
- Write one action arc + one final payoff.
- Add minimal constraints for continuity.
Always show full prompt and all params before submit, then wait for explicit confirmation.
@asset layered referencing
Use explicit role mapping in prompt drafts:
- Visual anchor:
@图片1 / @图1
- Camera/motion style:
参考@视频1运镜
- Action rhythm:
参考@视频2动作节奏
- Music/sound bed:
@音频1用于配乐
Good:
@图1为首帧,参考@视频1的跑步动作,镜头从正面切到侧面,@音频1做节奏底。
Bad:
High-value templates
Video extend
将@视频1延长 5s,新增段落为...,保持人物与场景连续。
- Set
duration to the added segment length.
Video fusion
- Decide which path fits the request:
text, image, multi-image, or first-frame/last-frame.
- Collect the user's brief,
duration, optional aspect_ratio, optional resolution, generate_audio (default true unless the user wants silent), and reference image URLs if the mode uses assets (prefer public https).
- Expand the prompt with the rules from
## Prompt expansion (mandatory). If the request needs tighter control, read references/seedance-prompt-optimization.md and explicitly decide mode, asset mapping, timeline beats, and negative constraints before writing the final prompt.
- If you are unsure about current multi-image support or field limits, run
node scripts/video_gen.js models --mode multi_image_to_video before a paid request.
- Show a confirmation table with the full expanded prompt, model, duration, aspect ratio, resolution, audio choice, and any image URLs.
- After explicit confirmation, run
node scripts/video_gen.js wait --json '...'.
- Return the JSON result. On success, surface the video URLs. On failure, report
errorCode and errorMessage and suggest the likely parameter fix.
CLI reference
# Check live model metadata
node scripts/video_gen.js models
node scripts/video_gen.js models --mode text_to_video
node scripts/video_gen.js models --mode image_to_video
node scripts/video_gen.js models --mode multi_image_to_video
# Text-to-video (non-empty model required; default audio on)
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"A paper crane unfolds into a real bird, cinematic lighting, 9:16 vertical. Audio: soft paper rustle, gentle whoosh, quiet room tone.","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'
# Single image to video
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"Animate this portrait with subtle hair and cloth movement. Audio: faint fabric rustle, subtle room ambience.","image":"https://example.com/frame.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'
# Multi-image to video
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"Turn these storyboard frames into one coherent reveal shot. Audio: light transition whooshes, soft underscore.","images":["https://example.com/1.png","https://example.com/2.png","https://example.com/3.png"],"duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'
# First-frame / last-frame guided video
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"Start on the first frame and transition naturally to the last frame with the same subject and environment. Audio: smooth morph tone, airy ambience.","first_frame":"https://example.com/start.png","last_frame":"https://example.com/end.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'
# WaveSpeed-style compatibility alias
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"Transition smoothly from the start image to the end image. Audio: soft blend whoosh, quiet room.","image":"https://example.com/start.png","last_image":"https://example.com/end.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'
# Preview without spending credits
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"A glowing koi swims through ink clouds. Audio: water shimmer, subtle chime.","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}' --dry-run
# Poll an existing task
node scripts/video_gen.js status --task-id <task-id>
Poll timeout classes
task_class=short: default 5 minutes (300000ms), intended for text-to-video.
task_class=long: default 20 minutes (1200000ms), intended for image/multi-image/almighty.
task_class=auto (default): infer from effective mode.
WERYAI_POLL_TIMEOUT_MS remains the highest-priority explicit override.
Compliance notice
- Do not store
WERYAI_API_KEY in repository files.
- Platform compliance for realistic human face references is handled by backend policy; this skill does not implement client-side blocking.
Definition of done
Done when the user receives at least one playable video URL, or a clear failure with errorCode / errorMessage and a concrete next step. The submitted payload must stay within the selected model's supported field set. With default generate_audio: true, the prompt should include Audio: prose unless the user requested silent generation.
Boundaries (out of scope)
- Do not use local file paths for references unless you have reviewed the assembled
scripts/video_gen.js and explicitly consent to local read-and-upload to WeryAI; otherwise prefer public https URLs.
- Do not invent undocumented API fields beyond the JSON surface in this skill.
- Do not assume multi-image or first/last-frame support without checking live metadata when the behavior matters.
- Do not store the secret value of
WERYAI_API_KEY inside the repository.
- Do not copy parameter names blindly from another provider without checking the normalized fields in this document.
Model & API constraints (frozen for this skill)
Frozen from the repository's current WeryAI capability snapshots. Re-run node scripts/video_gen.js models after platform upgrades.
Text-to-video (WERYDANCE_2_0)
| model_key |
durations |
aspect_ratios |
resolutions |
Audio |
negative_prompt |
Prompt max |
WERYDANCE_2_0 |
5, 10, 15 |
9:16, 1:1, 16:9 |
480p, 720p |
Yes |
No |
2000 |
Image-to-video (WERYDANCE_2_0)
| model_key |
durations |
aspect_ratios |
resolutions |
Audio |
negative_prompt |
upload_image_limit |
WERYDANCE_2_0 |
5, 10, 15 |
9:16, 1:1, 16:9 |
480p, 720p |
Yes |
No |
3 |
Multi-image and first-frame / last-frame
- Use the
images array for multi-image generation.
- Use either
images with ordered URLs, first_frame + last_frame, or image + last_image for start/end-frame control.
- Before a paid submission where multi-image support matters, run
node scripts/video_gen.js models --mode multi_image_to_video and confirm support_multiple_images, support_first_last_frame, upload_image_limit, and allowed output fields on the live account.
- If the live registry says the model cannot take multiple images, the runtime falls back to the first image only.
Default parameters
| Field |
Value |
| Model |
WERYDANCE_2_0 |
| Aspect ratio |
9:16 |
| Duration |
5 |
| Resolution |
720p |
| Audio |
true by default; expanded prompt must include Audio: unless the user wants silent |
| Prompt style |
concise cinematic English prompt with one clear motion beat and one final payoff |
Text brief -> Seedance video
Use this when the user has only an idea and wants Werydance 2.0 to generate the clip from scratch.
Need from the user:
- Subject or scene
- Motion beat
- Preferred aspect ratio or platform
- Optional duration and resolution
Flow:
Expand the brief into a full English prompt.
Keep model at WERYDANCE_2_0 unless the user explicitly wants another model.
Show a confirmation table:
📋 Ready to generate - please confirm
| Field |
This run |
Notes |
model |
WERYDANCE_2_0 |
Override only if the user explicitly requests another model |
aspect_ratio |
9:16 |
Must stay inside the Seedance row |
duration |
5 |
Allowed: 5 / 10 / 15 |
resolution |
720p |
Allowed: 480p / 720p |
generate_audio |
true |
Default on; Audio: in prompt unless user wants silent |
prompt |
full expanded prompt |
Never show only a summary |
After confirmation, run:
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"...","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'
Single reference image -> Seedance motion
Use this when the user already has one reference image and wants subtle or medium motion while preserving the subject.
Need from the user:
- One reference image URL (prefer public
https)
- Desired motion direction
- Optional duration, aspect ratio, and audio
Flow:
Expand the prompt around preservation plus motion.
Add image to the JSON body.
Confirm parameters and URL, then run:
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"...","image":"https://example.com/input.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'
Multiple reference images -> Seedance storyboard clip
Use this when the user wants several frames turned into one coherent shot or short sequence.
Need from the user:
- Ordered reference image URLs (prefer public
https)
- Desired transition logic
- Optional duration and aspect ratio
Flow:
Treat the image order as meaningful story order.
If support is uncertain, check models --mode multi_image_to_video first.
Confirm the final prompt plus ordered images, then run:
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"...","images":["https://example.com/1.png","https://example.com/2.png","https://example.com/3.png"],"duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'
First frame + last frame -> controlled transition
Use this when the user wants tighter motion control from a known opening frame to a known ending frame.
Need from the user:
- One reference start-frame URL (prefer public
https)
- One reference end-frame URL (prefer public
https)
- A prompt that explains the in-between action
Flow:
Expand the prompt so it explicitly bridges the first frame to the last frame.
Use either first_frame / last_frame, image / last_image, or pass the same two URLs through images in order.
Confirm both URLs and the full prompt, then run:
node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"...","first_frame":"https://example.com/start.png","last_frame":"https://example.com/end.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'
If the live registry rejects multi-image routing, reduce expectations: the runtime will fall back to single-image behavior with the first frame.
1---2name: seedance-2-video-gen3version: 1.0.14description: "Generate Werydance 2.0 videos through WeryAI for text-to-video, image-to-video, multi-image video, and first-frame/last-frame transitions. Use when you need a Werydance 2.0 video generator, want to animate a reference image (prefer a public https URL), create a storyboard-to-video clip, migrate `image + last_image` workflows, or generate controlled start/end frame video with your WeryAI API key."56tags: [seedance, seedance-2, video-gen, text-to-video, image-to-video, multi-image-video, almighty-reference, start-frame, end-frame, video-edit]78metadata:9 source: https://skillmd.com/skills/leoyeai-openclaw-master-skills/seedance-2-video-gen10 openclaw:11 emoji: 🎬12 primaryEnv: WERYAI_API_KEY13 paid: true14 network_required: true15 requires:16 env:17 - WERYAI_API_KEY18 bins:19 - node20 node: ">=18"21user-invocable: true22---2324# Werydance 2.0 video generator (almighty-ready)2526Generate Werydance 2.0 videos on WeryAI with one skill for text-to-video, image-to-video, first-frame/last-frame transition video, multi-image storyboard video, and almighty mixed-reference video generation.27Animate and transform scenes from single images, storyboard frames, or mixed references while keeping subject and motion continuity.2829**Dependencies:** `scripts/video_gen.js` at the skill package root (alongside `SKILL.md`) + `WERYAI_API_KEY` + Node.js 18+. No other Cursor skills are required.3031- text-only generation32- single-image animation33- multi-image storyboard generation34- first-frame/last-frame compatibility aliases35- almighty mixed references (`images + videos + audios + prompt`)3637Runtime secret: only `WERYAI_API_KEY`.3839## Core upgrade4041This skill now supports four input modalities for richer control:4243- Image reference: composition, character, and detail lock44- Video reference: camera language, action rhythm, effect imitation45- Audio reference: mood and timing guidance46- Text prompt: intent and constraints4748Smart routing policy:4950- If payload includes `videos` or `audios`, route to `POST /v1/generation/almighty-reference-to-video`.51- Otherwise keep legacy routing (`text-to-video`, `image-to-video`, `multi-image-to-video`).5253## Prerequisites5455- `WERYAI_API_KEY` must be set.56- Node.js 18+.57- Prefer public `https` URLs for media.58- Local files are supported and auto-uploaded by this skill via `POST /v1/generation/upload-file`.5960```sh61export WERYAI_API_KEY="your_api_key_here"62```6364## Quick checks6566```sh67node scripts/video_gen.js models --mode text_to_video68node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"A glowing koi swims through ink clouds","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}' --dry-run69```7071## Modes and input shapes7273| Mode | Trigger | API route | Key fields |74|---|---|---|---|75| Text | no media refs | `/v1/generation/text-to-video` | `prompt`, `duration`, optional `aspect_ratio`, `resolution`, `generate_audio` |76| Single image | `image` only | `/v1/generation/image-to-video` | `image`, `prompt`, plus common fields |77| Multi image | `images` only | `/v1/generation/multi-image-to-video` | `images`, `prompt`, plus common fields |78| Almighty | has `videos` or `audios` | `/v1/generation/almighty-reference-to-video` | `images`, `videos`, `audios`, `prompt`, `video_number`, plus common fields |7980Compatibility aliases still supported:8182- `first_frame + last_frame` -> normalized to ordered `images`83- `image + last_image` -> normalized to ordered `images`8485## Almighty constraints8687Almighty validations in this skill:8889- `prompt` max 500 chars90- `images` <= 991- `videos` <= 392- `audios` <= 393- mixed file total (`images + videos + audios`) <= 1294- at least one of `images` or `videos`95- `duration` must be 5-15 seconds96- `video_number` must be 1-49798Notes:99100- Backend enforces media-duration constraints for reference clips.101- Per current OpenAPI contract, almighty duration floor is 5s.102103## Local upload behavior104105Supported local files before generation submit:106107- Images: `jpg/jpeg/png/webp/gif`, max 10MB108- Videos: `mp4/mov`, max 50MB109- Audios: `mp3/wav`, max 50MB110111Upload endpoint used by this skill:112113- Shot scale, angle, and lens feel.114- Camera movement or a clear lock-off choice.115- Lighting direction, material response, and overall mood.116- Subject motion paced to the selected `duration`.117- One clear visual payoff in the final shot.118- Output framing such as `9:16 vertical` when using the default aspect ratio.119- **Audio (default-on):** Add a labeled **`Audio:`** block (ambience, layered SFX, subtle foley—**generic**, non-copyrighted) **even if the user never mentioned sound**. JSON **`generate_audio`** defaults to **`true`** for models that support audio; use **`false`** and omit **`Audio:`** only when the user explicitly wants **silent** output.120121Dry-run behavior:122123- `--dry-run` never uploads local files124- output includes `uploadPreview` to show which local paths would be uploaded125126## Prompt workflow (mandatory)127128Before paid submit, expand brief into production prompt:1291301. Decide mode.1312. Map each media to explicit role.1323. Build 2-4 timeline beats by duration.1334. Write one action arc + one final payoff.1345. Add minimal constraints for continuity.135136Always show full prompt and all params before submit, then wait for explicit confirmation.137138## @asset layered referencing139140Use explicit role mapping in prompt drafts:141142- Visual anchor: `@图片1` / `@图1`143- Camera/motion style: `参考@视频1运镜`144- Action rhythm: `参考@视频2动作节奏`145- Music/sound bed: `@音频1用于配乐`146147Good:148149- `@图1为首帧,参考@视频1的跑步动作,镜头从正面切到侧面,@音频1做节奏底。`150151Bad:152153- `用这些素材生成一个视频。`154155## High-value templates156157### Video extend158159- `将@视频1延长 5s,新增段落为...,保持人物与场景连续。`160- Set `duration` to the added segment length.161162### Video fusion1631641. Decide which path fits the request: `text`, `image`, `multi-image`, or `first-frame/last-frame`.1652. Collect the user's brief, `duration`, optional `aspect_ratio`, optional `resolution`, **`generate_audio`** (default **`true`** unless the user wants silent), and reference image URLs if the mode uses assets (prefer public `https`).1663. Expand the prompt with the rules from `## Prompt expansion (mandatory)`. If the request needs tighter control, read `references/seedance-prompt-optimization.md` and explicitly decide mode, asset mapping, timeline beats, and negative constraints before writing the final prompt.1674. If you are unsure about current multi-image support or field limits, run `node scripts/video_gen.js models --mode multi_image_to_video` before a paid request.1685. Show a confirmation table with the **full expanded prompt**, model, duration, aspect ratio, resolution, audio choice, and any image URLs.1696. After explicit confirmation, run `node scripts/video_gen.js wait --json '...'`.1707. Return the JSON result. On success, surface the video URLs. On failure, report `errorCode` and `errorMessage` and suggest the likely parameter fix.171172## CLI reference173174```sh175# Check live model metadata176node scripts/video_gen.js models177node scripts/video_gen.js models --mode text_to_video178node scripts/video_gen.js models --mode image_to_video179node scripts/video_gen.js models --mode multi_image_to_video180181# Text-to-video (non-empty model required; default audio on)182node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"A paper crane unfolds into a real bird, cinematic lighting, 9:16 vertical. Audio: soft paper rustle, gentle whoosh, quiet room tone.","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'183184# Single image to video185node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"Animate this portrait with subtle hair and cloth movement. Audio: faint fabric rustle, subtle room ambience.","image":"https://example.com/frame.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'186187# Multi-image to video188node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"Turn these storyboard frames into one coherent reveal shot. Audio: light transition whooshes, soft underscore.","images":["https://example.com/1.png","https://example.com/2.png","https://example.com/3.png"],"duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'189190# First-frame / last-frame guided video191node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"Start on the first frame and transition naturally to the last frame with the same subject and environment. Audio: smooth morph tone, airy ambience.","first_frame":"https://example.com/start.png","last_frame":"https://example.com/end.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'192193# WaveSpeed-style compatibility alias194node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"Transition smoothly from the start image to the end image. Audio: soft blend whoosh, quiet room.","image":"https://example.com/start.png","last_image":"https://example.com/end.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'195196# Preview without spending credits197node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"A glowing koi swims through ink clouds. Audio: water shimmer, subtle chime.","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}' --dry-run198199# Poll an existing task200node scripts/video_gen.js status --task-id <task-id>201```202203## Poll timeout classes204205- `task_class=short`: default `5` minutes (`300000ms`), intended for text-to-video.206- `task_class=long`: default `20` minutes (`1200000ms`), intended for image/multi-image/almighty.207- `task_class=auto` (default): infer from effective mode.208- `WERYAI_POLL_TIMEOUT_MS` remains the highest-priority explicit override.209210## Compliance notice211212- Do not store `WERYAI_API_KEY` in repository files.213- Platform compliance for realistic human face references is handled by backend policy; this skill does not implement client-side blocking.214215## Definition of done216217Done when the user receives at least one playable video URL, or a clear failure with `errorCode` / `errorMessage` and a concrete next step. The submitted payload must stay within the selected model's supported field set. With default **`generate_audio`: `true`**, the **`prompt`** should include **`Audio:`** prose unless the user requested silent generation.218219## Boundaries (out of scope)220221- Do not use local file paths for references unless you have reviewed the assembled `scripts/video_gen.js` and explicitly consent to local read-and-upload to WeryAI; otherwise prefer public **`https`** URLs.222- Do not invent undocumented API fields beyond the JSON surface in this skill.223- Do not assume multi-image or first/last-frame support without checking live metadata when the behavior matters.224- Do not store the secret value of `WERYAI_API_KEY` inside the repository.225- Do not copy parameter names blindly from another provider without checking the normalized fields in this document.226227## Model & API constraints (frozen for this skill)228229> Frozen from the repository's current WeryAI capability snapshots. Re-run `node scripts/video_gen.js models` after platform upgrades.230231### Text-to-video (`WERYDANCE_2_0`)232233| model_key | durations | aspect_ratios | resolutions | Audio | negative_prompt | Prompt max |234|-----------|-----------|---------------|-------------|-------|-----------------|------------|235| `WERYDANCE_2_0` | 5, 10, 15 | 9:16, 1:1, 16:9 | 480p, 720p | Yes | No | 2000 |236237### Image-to-video (`WERYDANCE_2_0`)238239| model_key | durations | aspect_ratios | resolutions | Audio | negative_prompt | upload_image_limit |240|-----------|-----------|---------------|-------------|-------|-----------------|-------------------|241| `WERYDANCE_2_0` | 5, 10, 15 | 9:16, 1:1, 16:9 | 480p, 720p | Yes | No | 3 |242243### Multi-image and first-frame / last-frame244245- Use the `images` array for multi-image generation.246- Use either `images` with ordered URLs, `first_frame` + `last_frame`, or `image` + `last_image` for start/end-frame control.247- Before a paid submission where multi-image support matters, run `node scripts/video_gen.js models --mode multi_image_to_video` and confirm `support_multiple_images`, `support_first_last_frame`, `upload_image_limit`, and allowed output fields on the live account.248- If the live registry says the model cannot take multiple images, the runtime falls back to the first image only.249250---251252## Default parameters253254| Field | Value |255|-------|-------|256| Model | `WERYDANCE_2_0` |257| Aspect ratio | `9:16` |258| Duration | `5` |259| Resolution | `720p` |260| Audio | **`true`** by default; expanded **`prompt`** must include **`Audio:`** unless the user wants silent |261| Prompt style | concise cinematic English prompt with one clear motion beat and one final payoff |262263---264265## Text brief -> Seedance video266267Use this when the user has only an idea and wants Werydance 2.0 to generate the clip from scratch.268269**Need from the user:**270271- Subject or scene272- Motion beat273- Preferred aspect ratio or platform274- Optional duration and resolution275276**Flow:**2772781. Expand the brief into a full English prompt.2792. Keep `model` at `WERYDANCE_2_0` unless the user explicitly wants another model.2803. Show a confirmation table:281282 > 📋 **Ready to generate - please confirm**283 >284 > | Field | This run | Notes |285 > |-------|----------|-------|286 > | `model` | `WERYDANCE_2_0` | Override only if the user explicitly requests another model |287 > | `aspect_ratio` | `9:16` | Must stay inside the Seedance row |288 > | `duration` | `5` | Allowed: 5 / 10 / 15 |289 > | `resolution` | `720p` | Allowed: 480p / 720p |290 > | `generate_audio` | `true` | Default **on**; **`Audio:`** in **`prompt`** unless user wants silent |291 > | `prompt` | **full expanded prompt** | Never show only a summary |2922934. After confirmation, run:294295 ```sh296 node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"...","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'297 ```298299---300301## Single reference image -> Seedance motion302303Use this when the user already has one reference image and wants subtle or medium motion while preserving the subject.304305**Need from the user:**306307- One reference image URL (prefer public `https`)308- Desired motion direction309- Optional duration, aspect ratio, and audio310311**Flow:**3123131. Expand the prompt around preservation plus motion.3142. Add `image` to the JSON body.3153. Confirm parameters and URL, then run:316317 ```sh318 node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"...","image":"https://example.com/input.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'319 ```320321---322323## Multiple reference images -> Seedance storyboard clip324325Use this when the user wants several frames turned into one coherent shot or short sequence.326327**Need from the user:**328329- Ordered reference image URLs (prefer public `https`)330- Desired transition logic331- Optional duration and aspect ratio332333**Flow:**3343351. Treat the image order as meaningful story order.3362. If support is uncertain, check `models --mode multi_image_to_video` first.3373. Confirm the final prompt plus ordered `images`, then run:338339 ```sh340 node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"...","images":["https://example.com/1.png","https://example.com/2.png","https://example.com/3.png"],"duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'341 ```342343---344345## First frame + last frame -> controlled transition346347Use this when the user wants tighter motion control from a known opening frame to a known ending frame.348349**Need from the user:**350351- One reference start-frame URL (prefer public `https`)352- One reference end-frame URL (prefer public `https`)353- A prompt that explains the in-between action354355**Flow:**3563571. Expand the prompt so it explicitly bridges the first frame to the last frame.3582. Use either `first_frame` / `last_frame`, `image` / `last_image`, or pass the same two URLs through `images` in order.3593. Confirm both URLs and the full prompt, then run:360361 ```sh362 node scripts/video_gen.js wait --json '{"model":"WERYDANCE_2_0","prompt":"...","first_frame":"https://example.com/start.png","last_frame":"https://example.com/end.png","duration":5,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}'363 ```3643654. If the live registry rejects multi-image routing, reduce expectations: the runtime will fall back to single-image behavior with the first frame.