diff --git a/.vscode/launch.json b/.vscode/launch.json index c1ff940..2ee144e 100644 --- a/.vscode/launch.json +++ b/.vscode/launch.json @@ -10,7 +10,7 @@ "justMyCode": true, "args": [ "--prompt=马云在直播间卖红薯", - "--model=gpt-image-2" + "--model=gpt-image-2.5-flare" ], "env": { "ROBOT_WECHAT_CLIENT_PORT": "9001", diff --git a/skills/image-to-image/SKILL.md b/skills/image-to-image/SKILL.md index 9e6b473..978ec1a 100644 --- a/skills/image-to-image/SKILL.md +++ b/skills/image-to-image/SKILL.md @@ -13,6 +13,8 @@ description: "图片修改、图生图工具。基于输入的一张或多张图 从数据库中读取绘图配置（API 密钥、Base URL 等），根据用户选择的模型调用对应的绘图 API，返回生成的图片 URL。 +OpenAI 默认模型为 `gpt-image-2.5-flare`；用户指定 OpenAI 但未指定具体模型时，传入此模型名。 + 这个仓库里额外提供了一个可执行脚本 `scripts/image_to_image.py`，方便宿主机器人直接调用。 ## 触发条件 @@ -36,7 +38,7 @@ description: "图片修改、图生图工具。基于输入的一张或多张图 }, "model": { "type": "string", - "description": "画图模型选择（可选）：即梦4.5(jimeng-4.5) / 即梦4.6(jimeng-4.6) / 即梦4.7(jimeng-4.7) / 即梦5.0(jimeng-5.0) / 即梦5.0 Pro(jimeng-5.0-pro) / 豆包5.0 Pro(doubao-seedream-5-0-pro) / 豆包5.0 Lite(doubao-seedream-5-0) / 豆包图生图(doubao-seededit-3.0-i2i) / 造相基础版(Z-Image) / 造相蒸馏版(Z-Image-Turbo) / 造相图片编辑(Qwen-Image-Edit-2511) / OpenAI GPT Image(gpt-image-2)，默认: 空(none)。", + "description": "画图模型选择（可选）：即梦4.5(jimeng-4.5) / 即梦4.6(jimeng-4.6) / 即梦4.7(jimeng-4.7) / 即梦5.0(jimeng-5.0) / 即梦5.0 Pro(jimeng-5.0-pro) / 豆包5.0 Pro(doubao-seedream-5-0-pro) / 豆包5.0 Lite(doubao-seedream-5-0) / 豆包图生图(doubao-seededit-3.0-i2i) / 造相基础版(Z-Image) / 造相蒸馏版(Z-Image-Turbo) / 造相图片编辑(Qwen-Image-Edit-2511) / OpenAI gpt-image-2(gpt-image-2) / OpenAI gpt-image-2.5(gpt-image-2.5-flare) / OpenAI gpt-image-2.5 Pro(gpt-image-2.5-sunburst)，默认: 空(none)。", "enum": [ "none", "jimeng-4.5", @@ -50,7 +52,9 @@ description: "图片修改、图生图工具。基于输入的一张或多张图 "Z-Image", "Z-Image-Turbo", "Qwen-Image-Edit-2511", - "gpt-image-2" + "gpt-image-2", + "gpt-image-2.5-flare", + "gpt-image-2.5-sunburst" ], "default": "none" }, diff --git a/skills/image-to-image/scripts/image_to_image.py b/skills/image-to-image/scripts/image_to_image.py index be71626..81f6730 100644 --- a/skills/image-to-image/scripts/image_to_image.py +++ b/skills/image-to-image/scripts/image_to_image.py @@ -590,7 +590,7 @@ def call_openai(config: dict, prompt: str, model: str, images: list[str], input_files = [path.open("rb") for path in input_paths] try: kwargs = { - "model": model or "gpt-image-2", + "model": model or "gpt-image-2.5-flare", "prompt": _openai_prompt(prompt, negative_prompt), "image": input_files, "n": _coerce_int(config.get("n"), 1, 1, 10), @@ -618,7 +618,7 @@ def call_openai(config: dict, prompt: str, model: str, images: list[str], JIMENG_MODELS = {"jimeng-4.5", "jimeng-4.6", "jimeng-4.7", "jimeng-5.0", "jimeng-5.0-pro"} DOUBAO_MODELS = {"doubao-seedream-5-0-pro", "doubao-seedream-5-0", "doubao-seededit-3.0-i2i"} ZIMAGE_MODELS = {"Z-Image", "Z-Image-Turbo", "Qwen-Image-Edit-2511"} -OPENAI_MODELS = {"gpt-image-2"} +OPENAI_MODELS = {"gpt-image-2", "gpt-image-2.5-flare", "gpt-image-2.5-sunburst"} def _parse_cli_params(argv: list[str]) -> dict: diff --git a/skills/text-to-image/SKILL.md b/skills/text-to-image/SKILL.md index f989fa1..858fa2e 100644 --- a/skills/text-to-image/SKILL.md +++ b/skills/text-to-image/SKILL.md @@ -11,6 +11,8 @@ description: "AI绘图工具，当用户想通过文本生成图像时，可以 从数据库中读取绘图配置（API 密钥、Base URL 等），根据用户选择的模型调用对应的绘图 API，返回生成的图片 URL。 +OpenAI 默认模型为 `gpt-image-2.5-flare`；用户指定 OpenAI 但未指定具体模型时，传入此模型名。 + 这个仓库里额外提供了一个可执行脚本 `scripts/text_to_image.py`，方便宿主机器人直接调用。 ## 触发条件 @@ -34,7 +36,7 @@ description: "AI绘图工具，当用户想通过文本生成图像时，可以 }, "model": { "type": "string", - "description": "画图模型选择（可选）：即梦4.5(jimeng-4.5) / 即梦4.6(jimeng-4.6) / 即梦4.7(jimeng-4.7) / 即梦5.0(jimeng-5.0) / 即梦5.0 Pro(jimeng-5.0-pro) / 豆包5.0 Pro(doubao-seedream-5-0-pro) / 豆包5.0 Lite(doubao-seedream-5-0) / 豆包4.5(doubao-seedream-4.5) / 豆包4.0(doubao-seedream-4.0) / 豆包文生图(doubao-seedream-3.0-t2i) / 豆包图生图(doubao-seededit-3.0-i2i) / 造相基础版(Z-Image) / 造相蒸馏版(Z-Image-Turbo) / 造相图片编辑(Qwen-Image-Edit-2511) / OpenAI GPT Image(gpt-image-2)，默认: 空(none)。", + "description": "画图模型选择（可选）：即梦4.5(jimeng-4.5) / 即梦4.6(jimeng-4.6) / 即梦4.7(jimeng-4.7) / 即梦5.0(jimeng-5.0) / 即梦5.0 Pro(jimeng-5.0-pro) / 豆包5.0 Pro(doubao-seedream-5-0-pro) / 豆包5.0 Lite(doubao-seedream-5-0) / 豆包4.5(doubao-seedream-4.5) / 豆包4.0(doubao-seedream-4.0) / 豆包文生图(doubao-seedream-3.0-t2i) / 豆包图生图(doubao-seededit-3.0-i2i) / 造相基础版(Z-Image) / 造相蒸馏版(Z-Image-Turbo) / 造相图片编辑(Qwen-Image-Edit-2511) / OpenAI gpt-image-2(gpt-image-2) / OpenAI gpt-image-2.5(gpt-image-2.5-flare) / OpenAI gpt-image-2.5 Pro(gpt-image-2.5-sunburst)，默认: 空(none)。", "enum": [ "none", "jimeng-4.5", @@ -51,7 +53,9 @@ description: "AI绘图工具，当用户想通过文本生成图像时，可以 "Z-Image", "Z-Image-Turbo", "Qwen-Image-Edit-2511", - "gpt-image-2" + "gpt-image-2", + "gpt-image-2.5-flare", + "gpt-image-2.5-sunburst" ], "default": "none" }, diff --git a/skills/text-to-image/scripts/text_to_image.py b/skills/text-to-image/scripts/text_to_image.py index 820ba05..289a440 100644 --- a/skills/text-to-image/scripts/text_to_image.py +++ b/skills/text-to-image/scripts/text_to_image.py @@ -563,7 +563,7 @@ def call_openai(config: dict, prompt: str, model: str, background = "auto" kwargs = { - "model": model or "gpt-image-2", + "model": model or "gpt-image-2.5-flare", "prompt": _openai_prompt(prompt, negative_prompt), "n": _coerce_int(config.get("n"), 1, 1, 10), "size": _openai_size(config, ratio, resolution), @@ -587,7 +587,7 @@ def call_openai(config: dict, prompt: str, model: str, JIMENG_MODELS = {"jimeng-4.5", "jimeng-4.6", "jimeng-4.7", "jimeng-5.0", "jimeng-5.0-pro"} DOUBAO_MODELS = {"doubao-seedream-5-0-pro", "doubao-seedream-5-0", "doubao-seedream-4.5", "doubao-seedream-4.0", "doubao-seedream-3.0-t2i", "doubao-seededit-3.0-i2i"} ZIMAGE_MODELS = {"Z-Image", "Z-Image-Turbo", "Qwen-Image-Edit-2511"} -OPENAI_MODELS = {"gpt-image-2"} +OPENAI_MODELS = {"gpt-image-2", "gpt-image-2.5-flare", "gpt-image-2.5-sunburst"} def _parse_cli_params(argv: list[str]) -> dict[str, str]: