@acedatacloud/skills 2026.629.0 → 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.
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@acedatacloud/skills",
|
|
3
|
-
"version": "2026.629.
|
|
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",
|
|
@@ -35,9 +35,7 @@ curl -X POST https://api.acedata.cloud/seedance/tasks \
|
|
|
35
35
|
|
|
36
36
|
## Models
|
|
37
37
|
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
The 2.0 series adds multimodal reference inputs: real-person / character **image** references, reference **audio**, and reference **video** (see the workflows below).
|
|
38
|
+
The Seedance 2.0 series adds multimodal reference inputs: real-person / character **image** references, reference **audio**, and reference **video** (see the workflows below).
|
|
41
39
|
|
|
42
40
|
| Model | Best For | Max resolution |
|
|
43
41
|
|-------|----------|----------------|
|
|
@@ -45,16 +43,6 @@ The 2.0 series adds multimodal reference inputs: real-person / character **image
|
|
|
45
43
|
| `doubao-seedance-2-0-fast-260128` | Faster 2.0 generation | `720p` |
|
|
46
44
|
| `doubao-seedance-2-0-mini-260615` | Lightweight / most cost-effective 2.0 | `720p` |
|
|
47
45
|
|
|
48
|
-
### Seedance 1.x
|
|
49
|
-
|
|
50
|
-
| Model | Type | Best For |
|
|
51
|
-
|-------|------|----------|
|
|
52
|
-
| `doubao-seedance-1-5-pro-251215` | Text+Image-to-Video | 1.5 flagship, audio support |
|
|
53
|
-
| `doubao-seedance-1-0-pro-250528` | Text+Image-to-Video | General-purpose, reliable quality |
|
|
54
|
-
| `doubao-seedance-1-0-pro-fast-251015` | Text+Image-to-Video | Faster Pro generation |
|
|
55
|
-
| `doubao-seedance-1-0-lite-t2v-250428` | Text-to-Video only | Lightweight text-to-video |
|
|
56
|
-
| `doubao-seedance-1-0-lite-i2v-250428` | Image-to-Video only | Lightweight image-to-video |
|
|
57
|
-
|
|
58
46
|
## Workflows
|
|
59
47
|
|
|
60
48
|
### 1. Text-to-Video
|
|
@@ -64,7 +52,7 @@ Pass a text content item in the `content` array.
|
|
|
64
52
|
```json
|
|
65
53
|
POST /seedance/videos
|
|
66
54
|
{
|
|
67
|
-
"model": "doubao-seedance-
|
|
55
|
+
"model": "doubao-seedance-2-0-260128",
|
|
68
56
|
"content": [
|
|
69
57
|
{"type": "text", "text": "a street dancer doing breakdancing moves in an urban setting"}
|
|
70
58
|
],
|
|
@@ -81,7 +69,7 @@ Include an image content item (with an optional `role`) alongside the text.
|
|
|
81
69
|
```json
|
|
82
70
|
POST /seedance/videos
|
|
83
71
|
{
|
|
84
|
-
"model": "doubao-seedance-
|
|
72
|
+
"model": "doubao-seedance-2-0-260128",
|
|
85
73
|
"content": [
|
|
86
74
|
{"type": "text", "text": "the person starts dancing gracefully"},
|
|
87
75
|
{
|
|
@@ -166,7 +154,7 @@ POST /seedance/videos
|
|
|
166
154
|
| `duration` | `2` – `15` | Duration in seconds (Seedance 2.0 supports 4–15) |
|
|
167
155
|
| `frames` | 29–361 (must satisfy 25+4n) | Frame count — mutually exclusive with `duration` |
|
|
168
156
|
| `seed` | -1 to 4294967295 | Seed for reproducible results (-1 = random) |
|
|
169
|
-
| `generate_audio` | `true` / `false` | Generate audio (supported by
|
|
157
|
+
| `generate_audio` | `true` / `false` | Generate audio (supported by the `doubao-seedance-2-0` series; other models ignore it) |
|
|
170
158
|
| `camerafixed` | `true` / `false` | Fix the camera position during generation |
|
|
171
159
|
| `watermark` | `true` / `false` | Add a watermark to the generated video |
|
|
172
160
|
| `return_last_frame` | `true` / `false` | Return the last frame of the generated video |
|
|
@@ -185,11 +173,11 @@ Supported inline params: `--rs` (resolution), `--rt` (ratio), `--dur` (duration)
|
|
|
185
173
|
|
|
186
174
|
## Gotchas
|
|
187
175
|
|
|
188
|
-
- Model names use the `doubao-*` convention (e.g. `doubao-seedance-
|
|
176
|
+
- Model names use the `doubao-*` convention (e.g. `doubao-seedance-2-0-260128`) — old short names like `seedance-1.0` are not valid
|
|
189
177
|
- The `content` array replaces the old `prompt` + `image_url` fields; always use `content`
|
|
190
178
|
- Image and text scenarios are mutually exclusive per content item — each item has either `text` or `image_url`, not both
|
|
191
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
|
|
192
|
-
- `generate_audio: true` is supported by
|
|
180
|
+
- `generate_audio: true` is supported by the `doubao-seedance-2-0` series; other models ignore this field
|
|
193
181
|
- Lite models are split: `*-lite-t2v-*` only accepts text, `*-lite-i2v-*` only accepts image-to-video
|
|
194
182
|
- `audio_url` and `video_url` reference items are used by the **Seedance 2.0 series only**
|
|
195
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
|