@acedatacloud/skills 2026.806.1 → 2026.807.1
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 +1 -1
- package/skills/minimax-video/SKILL.md +106 -0
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@acedatacloud/skills",
|
|
3
|
-
"version": "2026.
|
|
3
|
+
"version": "2026.807.1",
|
|
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",
|
|
@@ -0,0 +1,106 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: minimax-video
|
|
3
|
+
description: Generate MiniMax H3 videos from text, up to nine reference images, or up to three audio references through AceDataCloud. Use for text-to-video, multi-image video, audio-guided video, and MiniMax H3 task polling.
|
|
4
|
+
license: Apache-2.0
|
|
5
|
+
metadata:
|
|
6
|
+
author: acedatacloud
|
|
7
|
+
version: "1.0"
|
|
8
|
+
compatibility: Requires ACEDATACLOUD_API_TOKEN in .env (see _shared/authentication.md).
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
# MiniMax H3 Video Generation
|
|
12
|
+
|
|
13
|
+
Generate 4–15 second videos through `POST https://api.acedata.cloud/minimax/videos`.
|
|
14
|
+
|
|
15
|
+
> **Setup:** See [authentication](../_shared/authentication.md). For long jobs, use [async task polling](../_shared/async-tasks.md) with `POST /minimax/tasks`.
|
|
16
|
+
|
|
17
|
+
## Contract
|
|
18
|
+
|
|
19
|
+
| Parameter | Values | Default |
|
|
20
|
+
| --- | --- | --- |
|
|
21
|
+
| `model` | `minimax-h3` | `minimax-h3` |
|
|
22
|
+
| `prompt` | non-empty string, max 7000 chars | required |
|
|
23
|
+
| `image_urls` | 1–9 public HTTP(S) URLs | omitted |
|
|
24
|
+
| `audio_urls` | 1–3 public HTTP(S) URLs | omitted |
|
|
25
|
+
| `resolution` | `768P`, `2K` | `2K` |
|
|
26
|
+
| `ratio` | `16:9`, `9:16` | `16:9` |
|
|
27
|
+
| `aigc_watermark` | boolean | false |
|
|
28
|
+
| `duration` | integer 4–15 | 4 |
|
|
29
|
+
| `async` | boolean | false |
|
|
30
|
+
| `callback_url` | public HTTP(S) webhook | omitted |
|
|
31
|
+
|
|
32
|
+
`prompt` is required in every mode. Audio also requires at least one image. Mode inference is deterministic:
|
|
33
|
+
|
|
34
|
+
1. `audio_urls` present → audio-guided video
|
|
35
|
+
2. otherwise `image_urls` present → image-to-video
|
|
36
|
+
3. otherwise → text-to-video
|
|
37
|
+
|
|
38
|
+
Public pricing is **$0.057143/s for 768P** and **$0.091429/s for 2K** on the largest package. Failed tasks are not charged.
|
|
39
|
+
|
|
40
|
+
## Text to video
|
|
41
|
+
|
|
42
|
+
```bash
|
|
43
|
+
curl -X POST https://api.acedata.cloud/minimax/videos \
|
|
44
|
+
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
|
|
45
|
+
-H "Content-Type: application/json" \
|
|
46
|
+
-d '{
|
|
47
|
+
"model": "minimax-h3",
|
|
48
|
+
"prompt": "A red fox running through a snowy forest at dawn, low tracking shot",
|
|
49
|
+
"resolution": "768P",
|
|
50
|
+
"ratio": "16:9",
|
|
51
|
+
"duration": 4,
|
|
52
|
+
"async": true
|
|
53
|
+
}'
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
## Multi-image video
|
|
57
|
+
|
|
58
|
+
```json
|
|
59
|
+
{
|
|
60
|
+
"model": "minimax-h3",
|
|
61
|
+
"prompt": "Preserve the character and clothing while the camera slowly pushes in",
|
|
62
|
+
"image_urls": [
|
|
63
|
+
"https://cdn.acedata.cloud/b1c82e4937.png",
|
|
64
|
+
"https://cdn.acedata.cloud/eb75d88a3f.png"
|
|
65
|
+
],
|
|
66
|
+
"resolution": "768P",
|
|
67
|
+
"ratio": "9:16",
|
|
68
|
+
"duration": 8,
|
|
69
|
+
"async": true
|
|
70
|
+
}
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
## Audio-guided video
|
|
74
|
+
|
|
75
|
+
```json
|
|
76
|
+
{
|
|
77
|
+
"model": "minimax-h3",
|
|
78
|
+
"prompt": "A dancer moves naturally to the rhythm",
|
|
79
|
+
"image_urls": ["https://cdn.acedata.cloud/b1c82e4937.png"],
|
|
80
|
+
"audio_urls": ["https://cdn.acedata.cloud/6f7d62b18b.wav"],
|
|
81
|
+
"resolution": "768P",
|
|
82
|
+
"ratio": "9:16",
|
|
83
|
+
"duration": 8,
|
|
84
|
+
"async": true
|
|
85
|
+
}
|
|
86
|
+
```
|
|
87
|
+
|
|
88
|
+
## Poll a task
|
|
89
|
+
|
|
90
|
+
```bash
|
|
91
|
+
curl -X POST https://api.acedata.cloud/minimax/tasks \
|
|
92
|
+
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
|
|
93
|
+
-H "Content-Type: application/json" \
|
|
94
|
+
-d '{"action":"retrieve","id":"TASK_ID"}'
|
|
95
|
+
```
|
|
96
|
+
|
|
97
|
+
Continue polling about every five seconds until `response.success` is true or an error appears. Use `retrieve_batch` with `ids` to check several tasks in one request.
|
|
98
|
+
|
|
99
|
+
## Gotchas
|
|
100
|
+
|
|
101
|
+
- Do not send `action` to `/minimax/videos`; the API infers the mode from media inputs.
|
|
102
|
+
- `duration` must be an integer, not a decimal.
|
|
103
|
+
- Audio mode requires both `prompt` and at least one `image_urls` entry.
|
|
104
|
+
- Single-image mode uses the image as the first frame; multiple images are references.
|
|
105
|
+
- Use public URLs that the generation service can download.
|
|
106
|
+
- Returned videos are served from AceDataCloud CDN.
|