desirecore/market
2
0
Fork 0
mirror of https://git.openapi.site/https://github.com/desirecore/market.git synced 2026-07-23 07:03:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(dashscope-image-gen): 默认模型改为 gpt-image-2 v1.4.0 (#29)

Browse Source 
## Summary

上游 proxy (desirecore-cloud at api.yizhioa.cn) 仅支持 `gpt-image-2`
图片生成模型，`wan2.7-image` 返回 `model_price_error`。

The upstream proxy (desirecore-cloud) only supports `gpt-image-2` for
image generation. `wan2.7-image` returns `model_price_error`.

### Changes

- Default model changed from `wan2.7-image` → `gpt-image-2`
- `wan2.7-image` / `wan2.7-image-pro` kept as optional (requires
user-configured DashScope provider)
- Added auto-fallback strategy: `model_price_error` → retry with
`gpt-image-2`
- Size values adapted for gpt-image-2: `1536x1024` / `1024x1536`
- Skill display name updated: 阿里云 文生图 → AI 文生图
- Market version: 1.2.4 → 1.2.5, skill version: 1.3.0 → 1.4.0

### Test

- `gpt-image-2` via `/images/generations` endpoint: verified working
(b64_json response, 1.5MB PNG)
- Upload to media-store: verified working
- `dc-media://` rendering: verified working
This commit is contained in:
谢源祥
2026-06-15 01:14:53 +08:00
committed by GitHub
parent 19599c4051
commit 51f4837933
3 changed files with 63 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
manifest.json
View File

@@ -1,6 +1,6 @@
{ {
"name": "DesireCore Official Market", "name": "DesireCore Official Market",
"version": "1.2.4", "version": "1.2.5",
"schemaVersion": "1.1.0", "schemaVersion": "1.1.0",
"supportedLocales": ["zh-CN", "en-US"], "supportedLocales": ["zh-CN", "en-US"],
"defaultLocale": "en-US", "defaultLocale": "en-US",
@@ -28,7 +28,7 @@
"stats": { "stats": {
"totalAgents": 1, "totalAgents": 1,
"totalSkills": 25, "totalSkills": 25,
"lastUpdated": "2026-05-31" "lastUpdated": "2026-06-15"
}, },
"features": [ "features": [
"verified-only", "verified-only",

82
skills/dashscope-image-gen/SKILL.md
View File

@@ -1,14 +1,14 @@
--- ---
name: dashscope-image-gen name: dashscope-image-gen
description: >- description: >-
Use this skill when the user wants to generate images using Alibaba Cloud Use this skill when the user wants to generate images. Supports multiple
DashScope's Wan (通义万相) series models. Supports text-to-image with multiple models: gpt-image-2 (default, via DesireCore Cloud), wan2.7-image-pro and
model tiers (wan2.7-image-pro, wan2.7-image). Uses OpenAI-compatible wan2.7-image (when user has DashScope configured). Uses OpenAI-compatible
images/generations API for synchronous image generation. /images/generations API for synchronous image generation.
Use when 用户提到 生成图片、画图、文生图、创建图片、AI 绘画、 Use when the user mentions: generate image, draw, text-to-image, create image,
生成插图、画一张、帮我画、设计图片、通义万相、万相、阿里云画图、dashscope 画图。 AI painting, illustration, design picture.
license: Complete terms in LICENSE.txt license: Complete terms in LICENSE.txt
version: 1.3.0 version: 1.4.0
type: procedural type: procedural
risk_level: low risk_level: low
status: enabled status: enabled
@@ -25,7 +25,7 @@ requires:
- Bash - Bash
metadata: metadata:
author: desirecore author: desirecore
updated_at: '2026-06-10' updated_at: '2026-06-15'
i18n: i18n:
default_locale: en-US default_locale: en-US
source_locale: zh-CN source_locale: zh-CN
@@ -33,19 +33,22 @@ metadata:
- zh-CN - zh-CN
- en-US - en-US
zh-CN: zh-CN:
name: 阿里云 文生图 name: AI 文生图
short_desc: 基于阿里云通义万相的文本生成图片技能 short_desc: AI 文本生成图片技能（支持 GPT Image / 通义万相）
description: >- description: >-
当用户希望使用阿里云 DashScope 的通义万相系列模型生成图片时使用此技能。支持多种模型层级（wan2.7-image-pro / wan2.7-image）的文生图，通过 OpenAI 兼容的 images/generations API 同步生成图片。用户提到 生成图片、画图、文生图、创建图片、AI 绘画、生成插图、画一张、帮我画、设计图片、通义万相、万相、阿里云画图、dashscope 画图。 当用户希望生成图片时使用此技能。支持多种模型：gpt-image-2（默认，通过
DesireCore Cloud）、wan2.7-image-pro / wan2.7-image（用户自行配置阿里云
DashScope 时可用）。通过 OpenAI 兼容的 /images/generations API 同步生成图片。
用户提到 生成图片、画图、文生图、创建图片、AI 绘画、生成插图、画一张、帮我画、设计图片。
body: ./SKILL.zh-CN.md body: ./SKILL.zh-CN.md
source_hash: sha256:a2c4e8f01b3d5e7f source_hash: sha256:b3d5f7a91c2e4068
translated_by: human translated_by: human
en-US: en-US:
name: DashScope Image Generation name: AI Image Generation
short_desc: Text-to-image generation using Alibaba Cloud Wan (通义万相) models short_desc: AI text-to-image generation (GPT Image / Wan models)
description: "Use this skill when the user wants to generate images using Alibaba Cloud DashScope's Wan (通义万相) series models. Supports text-to-image with multiple model tiers (wan2.7-image-pro, wan2.7-image) via the OpenAI-compatible images/generations API. Trigger keywords: generate image, draw, text-to-image, create image, AI painting, illustration, design picture, Wan, Tongyi Wanxiang, DashScope." description: "Use this skill when the user wants to generate images. Supports multiple models: gpt-image-2 (default via DesireCore Cloud), wan2.7-image-pro / wan2.7-image (when user has DashScope configured). Uses the OpenAI-compatible /images/generations API. Trigger keywords: generate image, draw, text-to-image, create image, AI painting, illustration, design picture."
body: ./SKILL.md body: ./SKILL.md
source_hash: sha256:a2c4e8f01b3d5e7f source_hash: sha256:b3d5f7a91c2e4068
translated_by: human translated_by: human
market: market:
icon: >- icon: >-
@@ -56,7 +59,7 @@ market:
fill-opacity="0.4" stroke="#34C759" stroke-width="1.2" fill-opacity="0.4" stroke="#34C759" stroke-width="1.2"
stroke-linejoin="round"/><circle cx="15.5" cy="8.5" r="1.5" fill="#34C759" stroke-linejoin="round"/><circle cx="15.5" cy="8.5" r="1.5" fill="#34C759"
fill-opacity="0.6"/></svg> fill-opacity="0.6"/></svg>
short_desc: 基于阿里云通义万相的文本生成图片技能 short_desc: AI text-to-image generation (GPT Image / Wan models)
category: media category: media
maintainer: maintainer:
name: DesireCore Official name: DesireCore Official
@@ -69,7 +72,7 @@ market:
## Mandatory Rules (violations cause failure) ## Mandatory Rules (violations cause failure)
1. **STRICTLY follow the execution steps below** — do NOT improvise, explore alternative endpoints, or try models not listed in this document 1. **STRICTLY follow the execution steps below** — do NOT improvise, explore alternative endpoints, or try models not listed in this document
2. **Must access agent-service over HTTPS** — the API address is already provided in the system prompt under "本机 API" section (e.g. `https://127.0.0.1:PORT`); use it directly with `-k` to skip certificate verification 2. **Must access agent-service over HTTPS** — the API address is already provided in the system prompt under the local API section (e.g. `https://127.0.0.1:PORT`); use it directly with `-k` to skip certificate verification
3. **Must upload to media-store via `/api/media/upload`** — `/tmp` is only a transient download/decode location, never use a local path as the final output 3. **Must upload to media-store via `/api/media/upload`** — `/tmp` is only a transient download/decode location, never use a local path as the final output
4. **Must use the `dc-media://` protocol to display images** — the only form the frontend can render correctly 4. **Must use the `dc-media://` protocol to display images** — the only form the frontend can render correctly
5. **Use Bash curl throughout** — do not use the HttpRequest tool or Python 5. **Use Bash curl throughout** — do not use the HttpRequest tool or Python
@@ -78,27 +81,27 @@ market:
## Provider & Default Compute ## Provider & Default Compute
This skill uses Alibaba Cloud DashScope's Wan (通义万相) models. You do NOT need to specify a provider — just pass `"serviceType": "image_gen"` and the system will automatically route to the correct provider: You do NOT need to specify a provider — just pass `"serviceType": "image_gen"` and the system will automatically route to the correct provider.
- **DesireCore Cloud** (default, always available): The built-in compute provider already supports `image_gen` with Wan models. Users can generate images immediately without any configuration.
- **DashScope** (user-configured): If the user has configured their own DashScope API key, the system may route to it.
**Never** try to query provider lists, read compute.json, or explore available models through API calls. The models listed below are guaranteed to work. **Never** try to query provider lists, read compute.json, or explore available models through API calls. The models listed below are guaranteed to work.
## Model Selection ## Model Selection
| Model | Characteristics | When to use | | Model | Characteristics | When to use |
|------|------|---------| |-------|----------------|-------------|
| wan2.7-image-pro | Flagship, 4K resolution, thinking_mode | User asks for top quality, 4K, or rich detail | | gpt-image-2 | High quality, fast, versatile styles | **Default** — use when user does not specify a model |
| wan2.7-image | Standard high quality, thinking_mode | **Default**, for unspecified requests | | wan2.7-image | Standard high quality (requires DashScope provider) | Only when user explicitly asks for Wan / DashScope |
| wan2.7-image-pro | Flagship, 4K resolution (requires DashScope provider) | Only when user explicitly asks for top quality Wan model |
**Default rule**: if the user does not specify a model, use `wan2.7-image`. **Default rule**: if the user does not specify a model, use `gpt-image-2`.
**Note**: `wan2.7-image` and `wan2.7-image-pro` only work when the user has configured their own Alibaba Cloud DashScope provider. If you get an error with these models, fall back to `gpt-image-2`.
## Full Execution Flow (strictly follow these steps) ## Full Execution Flow (strictly follow these steps)
### How to get the API address ### How to get the API address
The system prompt already contains the agent-service API address under "本机 API" (e.g. `Agent Service: https://127.0.0.1:61000`). Extract the URL from there and use it directly. The system prompt already contains the agent-service API address under the local API section (e.g. `Agent Service: https://127.0.0.1:61000`). Extract the URL from there and use it directly.
If for any reason you cannot find it in the system prompt, use this fallback: If for any reason you cannot find it in the system prompt, use this fallback:
@@ -119,7 +122,7 @@ curl -sk -X POST "https://127.0.0.1:${PORT}/api/media-proxy" \
"serviceType": "image_gen", "serviceType": "image_gen",
"endpoint": "/images/generations", "endpoint": "/images/generations",
"body": { "body": {
"model": "wan2.7-image", "model": "gpt-image-2",
"prompt": "Replace this with the image description (English usually gives better results)", "prompt": "Replace this with the image description (English usually gives better results)",
"size": "1024x1024", "size": "1024x1024",
"n": 1 "n": 1
@@ -185,7 +188,7 @@ Pass `size` in the `body` object:
```json ```json
{ {
"model": "wan2.7-image", "model": "gpt-image-2",
"prompt": "your image description", "prompt": "your image description",
"size": "1024x1024", "size": "1024x1024",
"n": 1 "n": 1
@@ -193,15 +196,15 @@ Pass `size` in the `body` object:
``` ```
| User intent | size value | | User intent | size value |
|---------|-----------| |-------------|-----------|
| Square / avatar / default | "1024x1024" | | Square / avatar / default | "1024x1024" |
| Landscape / scenery / wallpaper | "1792x1024" | | Landscape / scenery / wallpaper | "1536x1024" |
| Portrait / mobile / poster | "1024x1792" | | Portrait / mobile / poster | "1024x1536" |
### Optional parameters (top-level body fields) ### Optional parameters (top-level body fields)
| Parameter | Description | | Parameter | Description |
|------|------| |-----------|-------------|
| `n` | Number of images, 1-4, default 1 | | `n` | Number of images, 1-4, default 1 |
| `size` | Image size, e.g. "1024x1024" | | `size` | Image size, e.g. "1024x1024" |
@@ -222,14 +225,15 @@ When `n > 1`, download and upload each image, then render them one by one:
| `"API Key not configured"` | API Key missing | Tell user to configure API key | | `"API Key not configured"` | API Key missing | Tell user to configure API key |
| `statusCode: 401` | API Key invalid or expired | Tell user to check API key | | `statusCode: 401` | API Key invalid or expired | Tell user to check API key |
| `statusCode: 429` | Rate limited | Wait and retry once | | `statusCode: 429` | Rate limited | Wait and retry once |
| `statusCode: 400` | Bad parameters | Check model name and size are from the tables above | | `statusCode: 400` + `model_price_error` | Model not available on current provider | Switch to `gpt-image-2` and retry |
| `statusCode: 403 AccessDenied.Unpurchased` | Model not activated | Tell user to enable the model in Alibaba Cloud console | | `statusCode: 400` | Other bad parameters | Check model name and size are from the tables above |
**On any error**: Do NOT try alternative models, alternative endpoints, or read config files. Report the error to the user clearly. **On model error**: If `wan2.7-image` or `wan2.7-image-pro` fails with `model_price_error`, automatically retry with `gpt-image-2`. Do NOT ask the user before retrying.
**On other errors**: Report the error to the user clearly. Do NOT try alternative endpoints or read config files.
## Notes ## Notes
- Image generation calls are synchronous and typically return in 10-60 seconds (wan2.7-image-pro can take longer) - Image generation calls are synchronous and typically return in 10-60 seconds
- Image URLs expire; download promptly
- English prompts usually produce the best results; Chinese is also supported - English prompts usually produce the best results; Chinese is also supported
- When the user does not specify a model or size, default to `wan2.7-image` + `1024x1024` - When the user does not specify a model or size, default to `gpt-image-2` + `1024x1024`

35
skills/dashscope-image-gen/SKILL.zh-CN.md
View File

@@ -14,10 +14,7 @@
## 供应商与默认算力 ## 供应商与默认算力
本技能使用阿里云 DashScope 的通义万相系列模型。**无需指定供应商**，只需传 `"serviceType": "image_gen"`，系统会自动路由到正确的供应商： **无需指定供应商**，只需传 `"serviceType": "image_gen"`，系统会自动路由到正确的供应商。
- **DesireCore Cloud**（默认，始终可用）：内置算力供应商已支持 `image_gen` 和通义万相模型。用户无需任何配置即可直接生成图片。
- **DashScope**（用户自配）：如果用户自己配置了阿里云 API Key，系统可能会路由到用户自己的供应商。
**禁止**尝试查询供应商列表、读取 compute.json、或通过 API 探索可用模型。下方列出的模型保证可用。 **禁止**尝试查询供应商列表、读取 compute.json、或通过 API 探索可用模型。下方列出的模型保证可用。
@@ -25,10 +22,13 @@
| 模型 | 特点 | 适用场景 | | 模型 | 特点 | 适用场景 |
|------|------|---------| |------|------|---------|
| wan2.7-image-pro | 旗舰，4K 分辨率，thinking_mode | 用户要求最高画质、4K、细节丰富 | | gpt-image-2 | 高画质，速度快，风格多样 | **默认首选** — 用户未指定模型时使用 |
| wan2.7-image | 标准高画质，thinking_mode | **默认首选**，无特殊要求时使用 | | wan2.7-image | 标准高画质（需配置阿里云 DashScope） | 仅当用户明确要求万相 / DashScope 时 |
| wan2.7-image-pro | 旗舰，4K 分辨率（需配置阿里云 DashScope） | 仅当用户明确要求最高画质万相模型时 |
**默认规则**：用户未指定模型时，使用 `wan2.7-image`。 **默认规则**：用户未指定模型时，使用 `gpt-image-2`。
**注意**：`wan2.7-image` 和 `wan2.7-image-pro` 仅在用户自行配置了阿里云 DashScope 供应商时可用。如果使用这些模型出错，自动降级到 `gpt-image-2`。
## 完整执行流程（严格按此步骤执行） ## 完整执行流程（严格按此步骤执行）
@@ -55,7 +55,7 @@ curl -sk -X POST "https://127.0.0.1:${PORT}/api/media-proxy" \
"serviceType": "image_gen", "serviceType": "image_gen",
"endpoint": "/images/generations", "endpoint": "/images/generations",
"body": { "body": {
"model": "wan2.7-image", "model": "gpt-image-2",
"prompt": "这里替换为图片描述（建议英文效果更好）", "prompt": "这里替换为图片描述（建议英文效果更好）",
"size": "1024x1024", "size": "1024x1024",
"n": 1 "n": 1
@@ -121,7 +121,7 @@ curl -sk -X POST "https://127.0.0.1:${PORT}/api/media/upload" \
```json ```json
{ {
"model": "wan2.7-image", "model": "gpt-image-2",
"prompt": "图片描述", "prompt": "图片描述",
"size": "1024x1024", "size": "1024x1024",
"n": 1 "n": 1
@@ -131,8 +131,8 @@ curl -sk -X POST "https://127.0.0.1:${PORT}/api/media/upload" \
| 用户意图 | size 参数 | | 用户意图 | size 参数 |
|---------|-----------| |---------|-----------|
| 正方形/头像/默认 | "1024x1024" | | 正方形/头像/默认 | "1024x1024" |
| 横版/风景/壁纸 | "1792x1024" | | 横版/风景/壁纸 | "1536x1024" |
| 竖版/手机/海报 | "1024x1792" | | 竖版/手机/海报 | "1024x1536" |
### 可选参数（加入请求体顶层） ### 可选参数（加入请求体顶层）
@@ -158,14 +158,15 @@ curl -sk -X POST "https://127.0.0.1:${PORT}/api/media/upload" \
| `"未配置 API Key"` | 未填写 API Key | 告知用户配置 API Key | | `"未配置 API Key"` | 未填写 API Key | 告知用户配置 API Key |
| `statusCode: 401` | API Key 无效或过期 | 告知用户检查 API Key | | `statusCode: 401` | API Key 无效或过期 | 告知用户检查 API Key |
| `statusCode: 429` | 频率限制 | 等待后重试一次 | | `statusCode: 429` | 频率限制 | 等待后重试一次 |
| `statusCode: 400` | 参数错误 | 检查模型名和尺寸是否在上表中 | | `statusCode: 400` + `model_price_error` | 模型在当前供应商不可用 | 切换到 `gpt-image-2` 重试 |
| `statusCode: 403 AccessDenied.Unpurchased` | 模型未开通 | 告知用户在阿里云控制台开通 | | `statusCode: 400` | 其他参数错误 | 检查模型名和尺寸是否在上表中 |
**遇到任何错误时**：禁止尝试其他模型、其他端点、或读取配置文件。直接向用户清晰报告错误即可。 **模型出错时**：如果 `wan2.7-image` 或 `wan2.7-image-pro` 报 `model_price_error`，自动切换到 `gpt-image-2` 重试。无需询问用户。
**其他错误时**：直接向用户清晰报告错误。禁止尝试其他端点或读取配置文件。
## 注意事项 ## 注意事项
- 图片生成调用是同步的，通常 10-60 秒返回（wan2.7-image-pro 可能更长） - 图片生成调用是同步的，通常 10-60 秒返回
- 结果图片 URL 有时效，必须及时下载
- 提示词建议用英文以获得最佳效果，中文也支持 - 提示词建议用英文以获得最佳效果，中文也支持
- 如果用户未明确要求模型/尺寸，默认使用 `wan2.7-image` + `1024x1024` - 如果用户未明确要求模型/尺寸，默认使用 `gpt-image-2` + `1024x1024`