@acedatacloud/skills 2026.628.7 → 2026.629.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/package.json +1 -1
  2. package/skills/seedance-video/SKILL.md +66 -14
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@acedatacloud/skills",
3
- "version": "2026.628.7",
3
+ "version": "2026.629.0",
4
4
  "description": "Agent Skills for AceDataCloud AI services — music, image, video generation, LLM chat, web search. Compatible with Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, and 30+ AI coding agents.",
5
5
  "keywords": [
6
6
  "agent-skills",
package/skills/seedance-video/SKILL.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: seedance-video
3
- description: Generate AI dance and motion videos with Seedance (ByteDance) via AceDataCloud API. Use when creating videos from text prompts or animating images into motion videos. Supports multiple models with configurable resolution, aspect ratio, duration, and optional audio generation.
3
+ description: Generate AI videos with Seedance (ByteDance) via AceDataCloud API. Use when creating videos from text prompts, animating images into motion videos, or driving Seedance 2.0 multimodal generation with real-person / character image references, reference audio, and reference video. Supports multiple models with configurable resolution (up to 4k), aspect ratio, duration, and optional audio generation.
4
4
  license: Apache-2.0
5
5
  metadata:
6
6
  author: acedatacloud
@@ -20,7 +20,7 @@ Generate AI dance and motion videos through AceDataCloud's Seedance (ByteDance)
20
20
  curl -X POST https://api.acedata.cloud/seedance/videos \
21
21
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
22
22
  -H "Content-Type: application/json" \
23
- -d '{"model": "doubao-seedance-1-0-pro-250528", "content": [{"type": "text", "text": "a dancer performing contemporary ballet in a misty forest"}], "callback_url": "https://api.acedata.cloud/health"}'
23
+ -d '{"model": "doubao-seedance-2-0-260128", "content": [{"type": "text", "text": "a dancer performing contemporary ballet in a misty forest"}], "callback_url": "https://api.acedata.cloud/health"}'
24
24
  ```
25
25
 
26
26
  > **Async:** See [async task polling](../_shared/async-tasks.md). Poll via `POST /seedance/tasks` with `{"id": "..."}`.
@@ -35,11 +35,23 @@ curl -X POST https://api.acedata.cloud/seedance/tasks \
35
35
 
36
36
  ## Models
37
37
 
38
+ ### Seedance 2.0 (current generation — multimodal reference)
39
+
40
+ The 2.0 series adds multimodal reference inputs: real-person / character **image** references, reference **audio**, and reference **video** (see the workflows below).
41
+
42
+ | Model | Best For | Max resolution |
43
+ |-------|----------|----------------|
44
+ | `doubao-seedance-2-0-260128` | Highest quality, real-person/character reference, 4k output | `4k` |
45
+ | `doubao-seedance-2-0-fast-260128` | Faster 2.0 generation | `720p` |
46
+ | `doubao-seedance-2-0-mini-260615` | Lightweight / most cost-effective 2.0 | `720p` |
47
+
48
+ ### Seedance 1.x
49
+
38
50
  | Model | Type | Best For |
39
51
  |-------|------|----------|
52
+ | `doubao-seedance-1-5-pro-251215` | Text+Image-to-Video | 1.5 flagship, audio support |
40
53
  | `doubao-seedance-1-0-pro-250528` | Text+Image-to-Video | General-purpose, reliable quality |
41
54
  | `doubao-seedance-1-0-pro-fast-251015` | Text+Image-to-Video | Faster Pro generation |
42
- | `doubao-seedance-1-5-pro-251215` | Text+Image-to-Video | Latest model, highest quality, audio support |
43
55
  | `doubao-seedance-1-0-lite-t2v-250428` | Text-to-Video only | Lightweight text-to-video |
44
56
  | `doubao-seedance-1-0-lite-i2v-250428` | Image-to-Video only | Lightweight image-to-video |
45
57
 
@@ -86,7 +98,11 @@ POST /seedance/videos
86
98
  Image roles:
87
99
  - `first_frame` — image is used as the opening frame
88
100
  - `last_frame` — image is used as the closing frame
89
- - `reference_image` — image is used as a style/content reference
101
+ - `reference_image` — image is used as a style / subject / real-person reference (Seedance 2.0 keeps the referenced person or character consistent)
102
+
103
+ Reference media (Seedance 2.0 only):
104
+ - `audio_url` — reference audio for voice timbre / background music (no `role`)
105
+ - `video_url` — reference video for subject, camera movement, motion or overall style (no `role`)
90
106
 
91
107
  ### 3. First-frame + Last-frame
92
108
 
@@ -95,7 +111,7 @@ Provide both a start and end frame image:
95
111
  ```json
96
112
  POST /seedance/videos
97
113
  {
98
- "model": "doubao-seedance-1-0-pro-250528",
114
+ "model": "doubao-seedance-2-0-260128",
99
115
  "content": [
100
116
  {"type": "text", "text": "smooth transition between two scenes"},
101
117
  {"type": "image_url", "role": "first_frame", "image_url": {"url": "https://example.com/start.jpg"}},
@@ -104,18 +120,53 @@ POST /seedance/videos
104
120
  }
105
121
  ```
106
122
 
123
+ ### 4. Real-person / character reference (Seedance 2.0)
124
+
125
+ Seedance 2.0 models (`doubao-seedance-2-0-260128`, `doubao-seedance-2-0-fast-260128`, `doubao-seedance-2-0-mini-260615`) can keep a **specific person or character** consistent across a brand-new scene. Pass one or more photos as `image_url` items with `role: "reference_image"` — the model preserves that subject's appearance. Up to 9 reference images are accepted.
126
+
127
+ ```json
128
+ POST /seedance/videos
129
+ {
130
+ "model": "doubao-seedance-2-0-260128",
131
+ "content": [
132
+ {"type": "text", "text": "the same person walking through a neon-lit night market, cinematic"},
133
+ {"type": "image_url", "role": "reference_image", "image_url": {"url": "https://example.com/person.jpg"}}
134
+ ],
135
+ "resolution": "1080p",
136
+ "duration": 8
137
+ }
138
+ ```
139
+
140
+ ### 5. Reference audio / video (Seedance 2.0)
141
+
142
+ 2.0 models also accept reference **audio** (voice timbre, background music) and reference **video** (subject content, camera movement, motion, overall style). Add `audio_url` and/or `video_url` content items. Limits: up to 3 audio and 3 video references per request.
143
+
144
+ ```json
145
+ POST /seedance/videos
146
+ {
147
+ "model": "doubao-seedance-2-0-260128",
148
+ "content": [
149
+ {"type": "text", "text": "a singer performing on stage, matching the reference voice and motion"},
150
+ {"type": "image_url", "role": "reference_image", "image_url": {"url": "https://example.com/person.jpg"}},
151
+ {"type": "audio_url", "audio_url": {"url": "https://example.com/voice.mp3"}},
152
+ {"type": "video_url", "video_url": {"url": "https://example.com/motion.mp4"}}
153
+ ],
154
+ "generate_audio": true
155
+ }
156
+ ```
157
+
107
158
  ## Parameters
108
159
 
109
160
  | Parameter | Values | Description |
110
161
  |-----------|--------|-------------|
111
162
  | `model` | see Models table | Model to use (required) |
112
- | `content` | array | Input items: text and/or image_url objects (required) |
113
- | `resolution` | `"480p"`, `"720p"`, `"1080p"` | Output resolution (default: 720p for pro, 480p for lite) |
163
+ | `content` | array | Input items: `text`, `image_url`, `audio_url` (2.0), `video_url` (2.0) (required) |
164
+ | `resolution` | `"480p"`, `"720p"`, `"1080p"`, `"4k"` | Output resolution. `4k` is `doubao-seedance-2-0-260128` (standard) only; `2-0-fast` / `2-0-mini` max out at `720p` (default: 720p for pro/2.0, 480p for lite) |
114
165
  | `ratio` | `"16:9"`, `"4:3"`, `"1:1"`, `"3:4"`, `"9:16"`, `"21:9"`, `"adaptive"` | Aspect ratio (default: 16:9) |
115
- | `duration` | `2` – `12` | Duration in seconds |
116
- | `frames` | 29–289 (must satisfy 25+4n) | Frame count — mutually exclusive with `duration` |
166
+ | `duration` | `2` – `15` | Duration in seconds (Seedance 2.0 supports 4–15) |
167
+ | `frames` | 29–361 (must satisfy 25+4n) | Frame count — mutually exclusive with `duration` |
117
168
  | `seed` | -1 to 4294967295 | Seed for reproducible results (-1 = random) |
118
- | `generate_audio` | `true` / `false` | Generate audio (only supported by `doubao-seedance-1-5-pro-251215`) |
169
+ | `generate_audio` | `true` / `false` | Generate audio (supported by `doubao-seedance-1-5-pro-251215` and the `doubao-seedance-2-0` series; other models ignore it) |
119
170
  | `camerafixed` | `true` / `false` | Fix the camera position during generation |
120
171
  | `watermark` | `true` / `false` | Add a watermark to the generated video |
121
172
  | `return_last_frame` | `true` / `false` | Return the last frame of the generated video |
@@ -137,12 +188,13 @@ Supported inline params: `--rs` (resolution), `--rt` (ratio), `--dur` (duration)
137
188
  - Model names use the `doubao-*` convention (e.g. `doubao-seedance-1-0-pro-250528`) — old short names like `seedance-1.0` are not valid
138
189
  - The `content` array replaces the old `prompt` + `image_url` fields; always use `content`
139
190
  - Image and text scenarios are mutually exclusive per content item — each item has either `text` or `image_url`, not both
140
- - `first_frame`, `last_frame`, and `reference_image` roles are mutually exclusive scenarios — pick one pattern per request
141
- - `generate_audio: true` is only supported by `doubao-seedance-1-5-pro-251215`; other models ignore this field
191
+ - `first_frame` and `last_frame` may be combined in one request, but `reference_image` is mutually exclusive with `first_frame` / `last_frame` — do not mix a reference image with first/last frames
192
+ - `generate_audio: true` is supported by `doubao-seedance-1-5-pro-251215` and the `doubao-seedance-2-0` series; other models ignore this field
142
193
  - Lite models are split: `*-lite-t2v-*` only accepts text, `*-lite-i2v-*` only accepts image-to-video
143
- - Resolution options are `480p`, `720p`, `1080p` — there is no 360p or 540p
194
+ - `audio_url` and `video_url` reference items are used by the **Seedance 2.0 series only**
195
+ - Resolution options are `480p`, `720p`, `1080p`, and `4k` (`4k` is `doubao-seedance-2-0-260128` only; `2-0-fast` / `2-0-mini` max out at `720p`) — there is no 360p or 540p
144
196
  - `service_tier` values are `"default"` and `"flex"` (not "standard"/"premium")
145
- - Duration range is **2–12 seconds** — values outside this range will fail
197
+ - Duration range is **2–15 seconds** (Seedance 2.0 supports 4–15) — values outside this range will fail
146
198
  - Task states use `"succeeded"` (not "completed") — check for this value when polling
147
199
 
148
200
  > **MCP:** `pip install mcp-seedance` | Hosted: `https://seedance.mcp.acedata.cloud/mcp` | See [all MCP servers](../_shared/mcp-servers.md)