@acedatacloud/skills 2026.628.7 → 2026.629.1

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 +63 -23
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@acedatacloud/skills",
3
- "version": "2026.628.7",
3
+ "version": "2026.629.1",
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": "..."}`.
@@ -35,13 +35,13 @@ curl -X POST https://api.acedata.cloud/seedance/tasks \
35
35
 
36
36
  ## Models
37
37
 
38
- | Model | Type | Best For |
39
- |-------|------|----------|
40
- | `doubao-seedance-1-0-pro-250528` | Text+Image-to-Video | General-purpose, reliable quality |
41
- | `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
- | `doubao-seedance-1-0-lite-t2v-250428` | Text-to-Video only | Lightweight text-to-video |
44
- | `doubao-seedance-1-0-lite-i2v-250428` | Image-to-Video only | Lightweight image-to-video |
38
+ The Seedance 2.0 series adds multimodal reference inputs: real-person / character **image** references, reference **audio**, and reference **video** (see the workflows below).
39
+
40
+ | Model | Best For | Max resolution |
41
+ |-------|----------|----------------|
42
+ | `doubao-seedance-2-0-260128` | Highest quality, real-person/character reference, 4k output | `4k` |
43
+ | `doubao-seedance-2-0-fast-260128` | Faster 2.0 generation | `720p` |
44
+ | `doubao-seedance-2-0-mini-260615` | Lightweight / most cost-effective 2.0 | `720p` |
45
45
 
46
46
  ## Workflows
47
47
 
@@ -52,7 +52,7 @@ Pass a text content item in the `content` array.
52
52
  ```json
53
53
  POST /seedance/videos
54
54
  {
55
- "model": "doubao-seedance-1-0-pro-250528",
55
+ "model": "doubao-seedance-2-0-260128",
56
56
  "content": [
57
57
  {"type": "text", "text": "a street dancer doing breakdancing moves in an urban setting"}
58
58
  ],
@@ -69,7 +69,7 @@ Include an image content item (with an optional `role`) alongside the text.
69
69
  ```json
70
70
  POST /seedance/videos
71
71
  {
72
- "model": "doubao-seedance-1-5-pro-251215",
72
+ "model": "doubao-seedance-2-0-260128",
73
73
  "content": [
74
74
  {"type": "text", "text": "the person starts dancing gracefully"},
75
75
  {
@@ -86,7 +86,11 @@ POST /seedance/videos
86
86
  Image roles:
87
87
  - `first_frame` — image is used as the opening frame
88
88
  - `last_frame` — image is used as the closing frame
89
- - `reference_image` — image is used as a style/content reference
89
+ - `reference_image` — image is used as a style / subject / real-person reference (Seedance 2.0 keeps the referenced person or character consistent)
90
+
91
+ Reference media (Seedance 2.0 only):
92
+ - `audio_url` — reference audio for voice timbre / background music (no `role`)
93
+ - `video_url` — reference video for subject, camera movement, motion or overall style (no `role`)
90
94
 
91
95
  ### 3. First-frame + Last-frame
92
96
 
@@ -95,7 +99,7 @@ Provide both a start and end frame image:
95
99
  ```json
96
100
  POST /seedance/videos
97
101
  {
98
- "model": "doubao-seedance-1-0-pro-250528",
102
+ "model": "doubao-seedance-2-0-260128",
99
103
  "content": [
100
104
  {"type": "text", "text": "smooth transition between two scenes"},
101
105
  {"type": "image_url", "role": "first_frame", "image_url": {"url": "https://example.com/start.jpg"}},
@@ -104,18 +108,53 @@ POST /seedance/videos
104
108
  }
105
109
  ```
106
110
 
111
+ ### 4. Real-person / character reference (Seedance 2.0)
112
+
113
+ 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.
114
+
115
+ ```json
116
+ POST /seedance/videos
117
+ {
118
+ "model": "doubao-seedance-2-0-260128",
119
+ "content": [
120
+ {"type": "text", "text": "the same person walking through a neon-lit night market, cinematic"},
121
+ {"type": "image_url", "role": "reference_image", "image_url": {"url": "https://example.com/person.jpg"}}
122
+ ],
123
+ "resolution": "1080p",
124
+ "duration": 8
125
+ }
126
+ ```
127
+
128
+ ### 5. Reference audio / video (Seedance 2.0)
129
+
130
+ 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.
131
+
132
+ ```json
133
+ POST /seedance/videos
134
+ {
135
+ "model": "doubao-seedance-2-0-260128",
136
+ "content": [
137
+ {"type": "text", "text": "a singer performing on stage, matching the reference voice and motion"},
138
+ {"type": "image_url", "role": "reference_image", "image_url": {"url": "https://example.com/person.jpg"}},
139
+ {"type": "audio_url", "audio_url": {"url": "https://example.com/voice.mp3"}},
140
+ {"type": "video_url", "video_url": {"url": "https://example.com/motion.mp4"}}
141
+ ],
142
+ "generate_audio": true
143
+ }
144
+ ```
145
+
107
146
  ## Parameters
108
147
 
109
148
  | Parameter | Values | Description |
110
149
  |-----------|--------|-------------|
111
150
  | `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) |
151
+ | `content` | array | Input items: `text`, `image_url`, `audio_url` (2.0), `video_url` (2.0) (required) |
152
+ | `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
153
  | `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` |
154
+ | `duration` | `2` – `15` | Duration in seconds (Seedance 2.0 supports 4–15) |
155
+ | `frames` | 29–361 (must satisfy 25+4n) | Frame count — mutually exclusive with `duration` |
117
156
  | `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`) |
157
+ | `generate_audio` | `true` / `false` | Generate audio (supported by the `doubao-seedance-2-0` series; other models ignore it) |
119
158
  | `camerafixed` | `true` / `false` | Fix the camera position during generation |
120
159
  | `watermark` | `true` / `false` | Add a watermark to the generated video |
121
160
  | `return_last_frame` | `true` / `false` | Return the last frame of the generated video |
@@ -134,15 +173,16 @@ Supported inline params: `--rs` (resolution), `--rt` (ratio), `--dur` (duration)
134
173
 
135
174
  ## Gotchas
136
175
 
137
- - Model names use the `doubao-*` convention (e.g. `doubao-seedance-1-0-pro-250528`) — old short names like `seedance-1.0` are not valid
176
+ - Model names use the `doubao-*` convention (e.g. `doubao-seedance-2-0-260128`) — old short names like `seedance-1.0` are not valid
138
177
  - The `content` array replaces the old `prompt` + `image_url` fields; always use `content`
139
178
  - 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
179
+ - `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
180
+ - `generate_audio: true` is supported by the `doubao-seedance-2-0` series; other models ignore this field
142
181
  - 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
182
+ - `audio_url` and `video_url` reference items are used by the **Seedance 2.0 series only**
183
+ - 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
184
  - `service_tier` values are `"default"` and `"flex"` (not "standard"/"premium")
145
- - Duration range is **2–12 seconds** — values outside this range will fail
185
+ - Duration range is **2–15 seconds** (Seedance 2.0 supports 4–15) — values outside this range will fail
146
186
  - Task states use `"succeeded"` (not "completed") — check for this value when polling
147
187
 
148
188
  > **MCP:** `pip install mcp-seedance` | Hosted: `https://seedance.mcp.acedata.cloud/mcp` | See [all MCP servers](../_shared/mcp-servers.md)