@acedatacloud/skills 2026.905.2 → 2026.909.0
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.
- package/README.md +1 -0
- package/package.json +1 -1
- package/skills/gpt-image-2-5/SKILL.md +52 -0
package/README.md
CHANGED
|
@@ -26,6 +26,7 @@ Compatible with **30+ AI coding agents** via the [agentskills.io](https://agents
|
|
|
26
26
|
|
|
27
27
|
| Skill | Description |
|
|
28
28
|
|-------|-------------|
|
|
29
|
+
| [gpt-image-2-5](skills/gpt-image-2-5/) | Generate and edit images with GPT Image 2.5 Flare or Sunburst |
|
|
29
30
|
| [flux-image](skills/flux-image/) | Generate and edit images with Flux (Black Forest Labs) |
|
|
30
31
|
| [qwen-image](skills/qwen-image/) | Generate and edit images with Qwen Image 3 |
|
|
31
32
|
| [seedream-image](skills/seedream-image/) | Generate and edit images with ByteDance Seedream |
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@acedatacloud/skills",
|
|
3
|
-
"version": "2026.
|
|
3
|
+
"version": "2026.909.0",
|
|
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",
|
|
@@ -0,0 +1,52 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: gpt-image-2-5
|
|
3
|
+
description: Generate or edit images with GPT Image 2.5 Flare or Sunburst through AceDataCloud. Choose Flare for speed or Sunburst for high-fidelity control; never use the unsupported bare gpt-image-2.5 name.
|
|
4
|
+
license: Apache-2.0
|
|
5
|
+
metadata:
|
|
6
|
+
author: acedatacloud
|
|
7
|
+
version: "1.0"
|
|
8
|
+
compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md).
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
# GPT Image 2.5
|
|
12
|
+
|
|
13
|
+
Use one exact model ID for every request:
|
|
14
|
+
|
|
15
|
+
- `gpt-image-2.5-flare` — faster generation.
|
|
16
|
+
- `gpt-image-2.5-sunburst` — higher-fidelity output and editing control.
|
|
17
|
+
|
|
18
|
+
Do not send `gpt-image-2.5`; it is not a model ID.
|
|
19
|
+
|
|
20
|
+
> **Setup:** See [authentication](../_shared/authentication.md) for token setup.
|
|
21
|
+
|
|
22
|
+
## Generate
|
|
23
|
+
|
|
24
|
+
```bash
|
|
25
|
+
curl -X POST https://api.acedata.cloud/openai/images/generations \
|
|
26
|
+
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
|
|
27
|
+
-H "Content-Type: application/json" \
|
|
28
|
+
-d '{"model":"gpt-image-2.5-flare","prompt":"A clean product photograph on a pale studio background, no text","size":"1024x1024","n":1}'
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
## Edit
|
|
32
|
+
|
|
33
|
+
```bash
|
|
34
|
+
curl -X POST https://api.acedata.cloud/openai/images/edits \
|
|
35
|
+
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
|
|
36
|
+
-F "model=gpt-image-2.5-sunburst" \
|
|
37
|
+
-F "prompt=Keep the subject and composition; change only the background to dark navy." \
|
|
38
|
+
-F "image=@input.png" \
|
|
39
|
+
-F "size=1024x1024" \
|
|
40
|
+
-F "n=1"
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
The result is in `data[].url`.
|
|
44
|
+
|
|
45
|
+
## Shared contract
|
|
46
|
+
|
|
47
|
+
- `size` may be `auto` or `WIDTHxHEIGHT`.
|
|
48
|
+
- Custom dimensions use multiples of 16, max side 3840, 655,360–8,294,400 pixels, and aspect ratio at most 3:1.
|
|
49
|
+
- `quality` accepts `auto`, `low`, `medium`, or `high`.
|
|
50
|
+
- `n` accepts 1–10 and billing uses the number of images returned. Use URL output for `n>1`; `b64_json` requires `n=1`.
|
|
51
|
+
- For long jobs, pass `async: true` or `callback_url`, then poll `POST /openai/tasks` with `{"id":"<task_id>"}`.
|
|
52
|
+
- Image editing accepts URL input in JSON or local files with multipart form data.
|