@acedatacloud/skills 2026.804.2 → 2026.805.0

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 (3) hide show
  1. package/package.json +1 -1
  2. package/skills/ai-chat/SKILL.md +7 -1
  3. package/skills/seedream-image/SKILL.md +5 -11
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@acedatacloud/skills",
3
- "version": "2026.804.2",
3
+ "version": "2026.805.0",
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/ai-chat/SKILL.md CHANGED
@@ -59,7 +59,7 @@ models include:
59
59
  | OpenAI / reasoning | `gpt-5.6-luna`, `gpt-5.6-terra`, `gpt-5.6-sol`, `gpt-5.5`, `gpt-5.5-pro`, `gpt-5.4`, `gpt-5.4-pro`, `gpt-5.2`, `gpt-5.1`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, `gpt-4o-mini`, `o1`, `o3`, `o4-mini` |
60
60
  | OpenAI free-tier chat-completions | `gpt-5.5:free`, `gpt-5:free`, `gpt-4.1:free`, `gpt-4o:free`, `gpt-4o-mini:free`, `gpt-oss:free` |
61
61
  | Claude | `claude-fable-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-opus-4-5-20251101`, `claude-sonnet-4-6`, `claude-sonnet-4-5-20250929`, `claude-sonnet-4-20250514`, `claude-haiku-4-5-20251001`, `claude-3-7-sonnet-20250219` |
62
- | Gemini | `gemini-3.5-flash`, `gemini-3.1-pro`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-image-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3-pro-preview`, `gemini-2.5-flash-lite`, `gemini-2.0-flash-lite` |
62
+ | Gemini | `gemini-3.5-flash`, `gemini-3.1-pro`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3-pro-preview`, `gemini-2.5-flash-lite`, `gemini-2.0-flash-lite` |
63
63
  | Grok | `grok-4.5`, `grok-4`, `grok-4-0709`, `grok-3`, `grok-3-fast` |
64
64
  | DeepSeek | `deepseek-r1`, `deepseek-r1-0528`, `deepseek-v3`, `deepseek-v3-250324`, `deepseek-v3.2-exp`, `deepseek-v4-flash` |
65
65
  | Kimi | `kimi-k3`, `kimi-k2.6`, `kimi-k2.5`, `kimi-k2-thinking-turbo`, `kimi-k2-thinking` |
@@ -68,6 +68,12 @@ models include:
68
68
  `/aichat2/conversations` also accepts `model_group` values
69
69
  `chatgpt`, `claude`, `gemini`, `grok`, `kimi`, `glm`, and `deepseek`.
70
70
 
71
+ > **Image-generating models are not chat models.** Names ending in `-image`
72
+ > (e.g. `gemini-*-image`, `gpt-4o-image`) are image-generation models and do
73
+ > not work on any chat surface listed above. Generate images through the
74
+ > dedicated endpoints instead — Gemini via
75
+ > `POST /v1beta/models/{model}:generateContent`, or `/nano-banana/images`.
76
+
71
77
  ## OpenAI-Compatible Chat
72
78
 
73
79
  ```json
package/skills/seedream-image/SKILL.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: seedream-image
3
- description: Generate and edit AI images with Seedream (ByteDance) via AceDataCloud API. Use when creating images from text prompts, editing existing images, or working with high-resolution outputs. Supports Seedream 3.0 T2I, 4.0, 4.5, 5.0, and SeedEdit 3.0 models.
3
+ description: Generate and edit AI images with Seedream (ByteDance) via AceDataCloud API. Use when creating images from text prompts, editing existing images, or working with high-resolution outputs. Supports Seedream 4.0, 4.5, and 5.0 models.
4
4
  license: Apache-2.0
5
5
  metadata:
6
6
  author: acedatacloud
@@ -31,8 +31,6 @@ curl -X POST https://api.acedata.cloud/seedream/images \
31
31
  | `doubao-seedream-5-0-260128` | Seedream 5.0 | Latest, highest quality (default) |
32
32
  | `doubao-seedream-4-5-251128` | Seedream 4.5 | High quality, balanced |
33
33
  | `doubao-seedream-4-0-250828` | Seedream 4.0 | Reliable generation |
34
- | `doubao-seedream-3-0-t2i-250415` | Seedream 3.0 T2I | Text-to-image, precise prompt following |
35
- | `doubao-seededit-3-0-i2i-250628` | SeedEdit 3.0 | Image-to-image editing |
36
34
 
37
35
  ## Workflows
38
36
 
@@ -49,13 +47,13 @@ POST /seedream/images
49
47
 
50
48
  ### 2. Image Editing (Image-to-Image)
51
49
 
52
- Edit an existing image by providing the source image URL(s) and a descriptive prompt. Use the `doubao-seededit-3-0-i2i-250628` model for best editing results.
50
+ Edit an existing image by providing the source image URL(s) and a descriptive prompt. Seedream 5.0 Pro, 5.0 Lite, 4.5, and 4.0 all support image input.
53
51
 
54
52
  ```json
55
53
  POST /seedream/images
56
54
  {
57
55
  "prompt": "change the sky to a golden sunset",
58
- "model": "doubao-seededit-3-0-i2i-250628",
56
+ "model": "doubao-seedream-5-0-260128",
59
57
  "image": ["https://example.com/photo.jpg"]
60
58
  }
61
59
  ```
@@ -88,9 +86,7 @@ POST /seedream/tasks
88
86
  |-----------|--------|-------------|
89
87
  | `model` | see Models table | Model to use (required) |
90
88
  | `prompt` | string | Image description (required) |
91
- | `size` | `"1K"`, `"2K"`, `"3K"`, `"4K"`, `"adaptive"` | Output resolution (e.g. `1K`=1024px, `2K`=2048px); `3K` only for Seedream 5.0 |
92
- | `seed` | integer [-1, 2147483647] | Seed for reproducibility (Seedream 3.0 T2I / SeedEdit 3.0 only) |
93
- | `guidance_scale` | number [1, 10] | Prompt adherence strength (3.0 models only; T2I default 2.5, edit default 5.5) |
89
+ | `size` | `"1K"`, `"2K"`, `"3K"`, `"4K"`, `"adaptive"` | Output resolution; available presets depend on the selected model |
94
90
  | `sequential_image_generation` | `"auto"`, `"disabled"` | Generate related images in sequence (5.0, 4.5, 4.0 only) |
95
91
  | `stream` | boolean | Stream images as they're generated (5.0, 4.5, 4.0 only) |
96
92
  | `watermark` | boolean | Add AI-generated watermark (default: true) |
@@ -111,9 +107,7 @@ POST /seedream/tasks
111
107
  - Model names now use the `doubao-*` naming convention (e.g. `doubao-seedream-5-0-260128`)
112
108
  - Image editing uses the same `/seedream/images` endpoint with the `image` array parameter (no separate edit endpoint)
113
109
  - `size` replaces separate `width`/`height` params; use `"1K"` for 1024×1024, `"2K"` for 2048×2048, etc.
114
- - `3K` size is only supported by Seedream 5.0; `adaptive` selects the best aspect ratio automatically
115
- - `seed` only works with `doubao-seedream-3-0-t2i-250415` and `doubao-seededit-3-0-i2i-250628`
116
- - `guidance_scale` is only available for the 3.0-series models
110
+ - 5.0 Pro supports `1K`/`2K`; 5.0 Lite supports `2K`/`3K`/`4K`; 4.5 supports `2K`/`4K`; 4.0 supports `1K`/`2K`/`4K`; `adaptive` selects a size from the reference image
117
111
  - `stream` and `sequential_image_generation` are only available for Seedream 5.0, 4.5, and 4.0
118
112
  - Pass `callback_url` to get a `task_id` immediately and avoid blocking; poll `/seedream/tasks` for the result — use `"https://api.acedata.cloud/health"` as a placeholder to force async mode without a real webhook
119
113