From 1c0f1432259a13c9fdf47af58746250305d8ea95 Mon Sep 17 00:00:00 2001 From: tt-P607 <68868379+tt-P607@users.noreply.github.com> Date: Tue, 16 Dec 2025 15:16:56 +0800 Subject: [PATCH] =?UTF-8?q?feat(maizone/ai-image):=20=E6=B7=BB=E5=8A=A0?= =?UTF-8?q?=E5=A4=9A=E6=8F=90=E4=BE=9B=E5=95=86=20AI=20=E5=9B=BE=E5=83=8F?= =?UTF-8?q?=E6=94=AF=E6=8C=81?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 此更改在 MaiZone 插件中引入了对多个 AI 图像生成提供商的强大支持，即 NovelAI 和 SiliconFlow。整个 AI 图像生成工作流程已被重新设计，以允许 LLM 为图像服务提供详细的提示，包括 NovelAI 的负面提示和纵横比。 重大更改：已移除本地图像发布功能。所有相关配置字段（`send.enable_image`、`send.image_number`、`send.image_directory`）已被移除。AI 图像生成配置已完全重建，并移动到新的专用部分（`ai_image`、`siliconflow`、`novelai`）。 --- .../built_in/maizone_refactored/plugin.py | 23 +- .../services/content_service.py | 259 +++++++++++++++- .../services/image_service.py | 77 +++-- .../services/novelai_service.py | 286 ++++++++++++++++++ .../services/qzone_service.py | 159 +++++----- 5 files changed, 698 insertions(+), 106 deletions(-) create mode 100644 src/plugins/built_in/maizone_refactored/services/novelai_service.py diff --git a/src/plugins/built_in/maizone_refactored/plugin.py b/src/plugins/built_in/maizone_refactored/plugin.py index 16ca4c7de..91d752464 100644 --- a/src/plugins/built_in/maizone_refactored/plugin.py +++ b/src/plugins/built_in/maizone_refactored/plugin.py @@ -43,19 +43,26 @@ class MaiZoneRefactoredPlugin(BasePlugin): "plugin": {"enable": ConfigField(type=bool, default=True, description="是否启用插件")}, "models": { "text_model": ConfigField(type=str, default="maizone", description="生成文本的模型名称"), - "siliconflow_apikey": ConfigField(type=str, default="", description="硅基流动AI生图API密钥"), + }, + "ai_image": { + "enable_ai_image": ConfigField(type=bool, default=False, description="是否启用AI生成配图"), + "provider": ConfigField(type=str, default="siliconflow", description="AI生图服务提供商（siliconflow/novelai）"), + "image_number": ConfigField(type=int, default=1, description="生成图片数量（1-4张）"), + }, + "siliconflow": { + "api_key": ConfigField(type=str, default="", description="硅基流动API密钥"), + }, + "novelai": { + "api_key": ConfigField(type=str, default="", description="NovelAI官方API密钥"), + "character_prompt": ConfigField(type=str, default="", description="Bot角色外貌描述（AI判断需要bot出镜时插入）"), + "base_negative_prompt": ConfigField(type=str, default="nsfw, nude, explicit, sexual content, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality", description="基础负面提示词（禁止不良内容）"), + "proxy_host": ConfigField(type=str, default="", description="代理服务器地址（如：127.0.0.1）"), + "proxy_port": ConfigField(type=int, default=0, description="代理服务器端口（如：7890）"), }, "send": { "permission": ConfigField(type=list, default=[], description="发送权限QQ号列表"), "permission_type": ConfigField(type=str, default="whitelist", description="权限类型"), - "enable_image": ConfigField(type=bool, default=False, description="是否启用说说配图"), - "enable_ai_image": ConfigField(type=bool, default=False, description="是否启用AI生成配图"), "enable_reply": ConfigField(type=bool, default=True, description="完成后是否回复"), - "ai_image_number": ConfigField(type=int, default=1, description="AI生成图片数量（1-4张）"), - "image_number": ConfigField(type=int, default=1, description="本地配图数量（1-9张）"), - "image_directory": ConfigField( - type=str, default=(Path(__file__).parent / "images").as_posix(), description="图片存储目录" - ), }, "read": { "permission": ConfigField(type=list, default=[], description="阅读权限QQ号列表"), diff --git a/src/plugins/built_in/maizone_refactored/services/content_service.py b/src/plugins/built_in/maizone_refactored/services/content_service.py index 1c1c63e3e..dd29cd4ae 100644 --- a/src/plugins/built_in/maizone_refactored/services/content_service.py +++ b/src/plugins/built_in/maizone_refactored/services/content_service.py @@ -54,9 +54,10 @@ class ContentService: logger.error("未配置LLM模型") return "" - # 获取机器人信息 - bot_personality = config_api.get_global_config("personality.personality_core", "一个机器人") - bot_expression = config_api.get_global_config("personality.reply_style", "内容积极向上") + # 获取机器人信息（核心人格配置） + bot_personality_core = config_api.get_global_config("personality.personality_core", "一个机器人") + bot_personality_side = config_api.get_global_config("personality.personality_side", "") + bot_reply_style = config_api.get_global_config("personality.reply_style", "内容积极向上") qq_account = config_api.get_global_config("bot.qq_account", "") # 获取当前时间信息 @@ -65,13 +66,20 @@ class ContentService: weekday_names = ["星期一", "星期二", "星期三", "星期四", "星期五", "星期六", "星期日"] weekday = weekday_names[now.weekday()] + # 构建人设描述 + personality_desc = f"你的核心人格：{bot_personality_core}" + if bot_personality_side: + personality_desc += f"\n你的人格侧面：{bot_personality_side}" + personality_desc += f"\n\n你的表达方式：{bot_reply_style}" + # 构建提示词 prompt_topic = f"主题是'{topic}'" if topic else "主题不限" prompt = f""" - 你是'{bot_personality}'，现在是{current_time}（{weekday}），你想写一条{prompt_topic}的说说发表在qq空间上。 - {bot_expression} +{personality_desc} - 请严格遵守以下规则： +现在是{current_time}（{weekday}），你想写一条{prompt_topic}的说说发表在qq空间上。 + +请严格遵守以下规则： 1. **绝对禁止**在说说中直接、完整地提及当前的年月日或几点几分。 2. 你应该将当前时间作为创作的背景，用它来判断现在是“清晨”、“傍晚”还是“深夜”。 3. 使用自然、模糊的词语来暗示时间，例如“刚刚”、“今天下午”、“夜深啦”等。 @@ -112,7 +120,244 @@ class ContentService: logger.error(f"生成说说内容时发生异常: {e}") return "" - async def generate_comment(self, content: str, target_name: str, rt_con: str = "", images: list = []) -> str: + async def generate_story_with_image_info( + self, topic: str, context: str | None = None + ) -> tuple[str, dict]: + """ + 生成说说内容，并同时生成NovelAI图片提示词信息 + + :param topic: 说说的主题 + :param context: 可选的聊天上下文 + :return: (说说文本, 图片信息字典) + 图片信息字典格式: { + "prompt": str, # NovelAI提示词（英文） + "negative_prompt": str, # 负面提示词（英文） + "include_character": bool, # 画面是否包含bot自己（true时插入角色外貌提示词） + "aspect_ratio": str # 画幅（方图/横图/竖图） + } + """ + try: + # 获取模型配置 + models = llm_api.get_available_models() + text_model = str(self.get_config("models.text_model", "replyer")) + model_config = models.get(text_model) + + if not model_config: + logger.error("未配置LLM模型") + return "", {"has_image": False} + + # 获取机器人信息（核心人格配置） + bot_personality_core = config_api.get_global_config("personality.personality_core", "一个机器人") + bot_personality_side = config_api.get_global_config("personality.personality_side", "") + bot_reply_style = config_api.get_global_config("personality.reply_style", "内容积极向上") + qq_account = config_api.get_global_config("bot.qq_account", "") + + # 获取角色外貌描述（用于告知LLM） + character_prompt = self.get_config("novelai.character_prompt", "") + + # 获取当前时间信息 + now = datetime.datetime.now() + current_time = now.strftime("%Y年%m月%d日 %H:%M") + weekday_names = ["星期一", "星期二", "星期三", "星期四", "星期五", "星期六", "星期日"] + weekday = weekday_names[now.weekday()] + + # 构建提示词 + prompt_topic = f"主题是'{topic}'" if topic else "主题不限" + + # 构建人设描述 + personality_desc = f"你的核心人格：{bot_personality_core}" + if bot_personality_side: + personality_desc += f"\n你的人格侧面：{bot_personality_side}" + personality_desc += f"\n\n你的表达方式：{bot_reply_style}" + + # 检查是否启用AI配图（统一开关） + ai_image_enabled = self.get_config("ai_image.enable_ai_image", False) + provider = self.get_config("ai_image.provider", "siliconflow") + + # NovelAI配图指引（内置） + novelai_guide = "" + output_format = '{"text": "说说正文内容"}' + + if ai_image_enabled and provider == "novelai": + # 构建角色信息提示 + character_info = "" + if character_prompt: + character_info = f""" +**角色特征锚点**（当include_character=true时会插入以下基础特征）： +``` +{character_prompt} +``` +📌 重要说明： +- 这只是角色的**基础外貌特征**（发型、眼睛、耳朵等固定特征），用于锚定角色身份 +- 你可以**自由描述**：衣服、动作、表情、姿势、装饰、配饰等所有可变元素 +- 例如：可以让角色穿不同风格的衣服（casual, formal, sportswear, dress等） +- 例如：可以设计各种动作（sitting, standing, walking, running, lying down等） +- 例如：可以搭配各种表情（smile, laugh, serious, thinking, surprised等） +- **鼓励创意**：根据说说内容自由发挥，让画面更丰富生动！ +""" + + novelai_guide = f""" +**配图说明：** +这条说说会使用NovelAI Diffusion模型（二次元风格）生成配图。 +{character_info} +**提示词生成要求（非常重要）：** +你需要生成一段详细的英文图片提示词，必须包含以下要素： + +1. **画质标签**（必需）： + - 开头必须加：masterpiece, best quality, detailed, high resolution + +2. **主体元素**（自由发挥）： + - 人物描述：表情、动作、姿态（**完全自由**，不受角色锚点限制） + - 服装搭配：casual clothing, dress, hoodie, school uniform, sportswear等（**任意选择**） + - 配饰装饰：hat, glasses, ribbon, jewelry, bag等（**随意添加**） + - 物体/场景：具体的物品、建筑、自然景观等 + +3. **场景与环境**（必需）： + - 地点：indoor/outdoor, cafe, park, bedroom, street, beach, forest等 + - 背景：描述背景的细节（sky, trees, buildings, ocean, mountains等） + +4. **氛围与风格**（必需）： + - 光线：sunlight, sunset, golden hour, soft lighting, dramatic lighting, night + - 天气/时间：sunny day, rainy, cloudy, starry night, dawn, dusk + - 整体氛围：peaceful, cozy, romantic, energetic, melancholic, playful + +5. **色彩与细节**（推荐）： + - 主色调：warm colors, cool tones, pastel colors, vibrant colors + - 特殊细节：falling petals, sparkles, lens flare, depth of field, bokeh + +6. **include_character字段**： + - true：画面中包含"你自己"（自拍、你在画面中的场景） + - false：画面中不包含你（风景、物品、他人） + +7. **negative_prompt（负面提示词）**： + - **严格禁止**以下内容：nsfw, nude, explicit, sexual content, violence, gore, blood + - 排除质量问题：lowres, bad anatomy, bad hands, deformed, mutilated, ugly + - 排除瑕疵：blurry, poorly drawn, worst quality, low quality, jpeg artifacts + - 可以自行补充其他不需要的元素 + +8. **aspect_ratio（画幅）**： + - 方图：适合头像、特写、正方形构图 + - 横图：适合风景、全景、宽幅场景 + - 竖图：适合人物全身、纵向构图 + +**内容审核规则（必须遵守）**： +- 🚫 严禁生成NSFW、色情、裸露、性暗示内容 +- 🚫 严禁生成暴力、血腥、恐怖、惊悚内容 +- 🚫 严禁生成肢体畸形、器官变异、恶心画面 +- ✅ 提示词必须符合健康、积极、美好的审美标准 +- ✅ 专注于日常生活、自然风景、温馨场景等正面内容 + +**创意自由度**： +- 💡 **衣服搭配**：可以自由设计各种服装风格（休闲、正式、运动、可爱、时尚等） +- 💡 **动作姿势**：站、坐、躺、走、跑、跳、伸展等任意动作 +- 💡 **表情情绪**：微笑、大笑、思考、惊讶、温柔、调皮等丰富表情 +- 💡 **场景创意**：根据说说内容自由发挥，让画面更贴合心情和主题 + +**示例提示词（展示多样性）**： +- 休闲风："masterpiece, best quality, 1girl, casual clothing, white t-shirt, jeans, sitting on bench, outdoor park, reading book, afternoon sunlight, relaxed atmosphere" +- 运动风："masterpiece, best quality, 1girl, sportswear, running in park, energetic, morning light, trees background, dynamic pose, healthy lifestyle" +- 咖啡馆："masterpiece, best quality, 1girl, sitting in cozy cafe, holding coffee cup, warm lighting, wooden table, books beside, peaceful atmosphere" +""" + output_format = '''{"text": "说说正文内容", "image": {"prompt": "详细的英文提示词（包含画质+主体+场景+氛围+光线+色彩）", "negative_prompt": "负面词", "include_character": true/false, "aspect_ratio": "方图/横图/竖图"}}''' + elif ai_image_enabled and provider == "siliconflow": + novelai_guide = """ +**配图说明：** +这条说说会使用AI生成配图。 + +**提示词生成要求（非常重要）：** +你需要生成一段详细的英文图片描述，必须包含以下要素： + +1. **主体内容**：画面的核心元素（人物/物体/场景） +2. **具体场景**：地点、环境、背景细节 +3. **氛围与风格**：整体感觉、光线、天气、色调 +4. **细节描述**：补充的视觉细节（动作、表情、装饰等） + +**示例提示词**： +- "a girl sitting in a modern cafe, warm afternoon lighting, wooden furniture, coffee cup on table, books beside her, cozy and peaceful atmosphere, soft focus background" +- "sunset over the calm ocean, golden hour, orange and purple sky, gentle waves, peaceful and serene mood, wide angle view" +- "cherry blossoms in spring, soft pink petals falling, blue sky, sunlight filtering through branches, peaceful park scene, gentle breeze" +""" + output_format = '''{"text": "说说正文内容", "image": {"prompt": "详细的英文描述（主体+场景+氛围+光线+细节）"}}''' + + prompt = f""" +{personality_desc} + +现在是{current_time}（{weekday}），你想写一条{prompt_topic}的说说发表在qq空间上。 + +**说说文本规则：** +1. **绝对禁止**在说说中直接、完整地提及当前的年月日或几点几分。 +2. 你应该将当前时间作为创作的背景，用它来判断现在是"清晨"、"傍晚"还是"深夜"。 +3. 使用自然、模糊的词语来暗示时间，例如"刚刚"、"今天下午"、"夜深啦"等。 +4. **内容简短**：总长度严格控制在100字以内。 +5. **禁止表情**：严禁使用任何Emoji表情符号。 +6. **严禁重复**：下方会提供你最近发过的说说历史，你必须创作一条全新的、与历史记录内容和主题都不同的说说。 +7. 不要刻意突出自身学科背景，不要浮夸，不要夸张修辞。 + +{novelai_guide} + +**输出格式（JSON）：** +{output_format} + +只输出JSON格式，不要有其他内容。 + """ + + # 如果有上下文，则加入到prompt中 + if context: + prompt += f"\n\n作为参考，这里有一些最近的聊天记录：\n---\n{context}\n---" + + # 添加历史记录以避免重复 + prompt += "\n\n---历史说说记录---\n" + history_block = await get_send_history(qq_account) + if history_block: + prompt += history_block + + # 调用LLM生成内容 + success, response, _, _ = await llm_api.generate_with_model( + prompt=prompt, + model_config=model_config, + request_type="story.generate_with_image", + temperature=0.3, + max_tokens=1500, + ) + + if success: + # 解析JSON响应 + import json5 + try: + # 提取JSON部分（去除可能的markdown代码块标记） + json_text = response.strip() + if json_text.startswith("```json"): + json_text = json_text[7:] + if json_text.startswith("```"): + json_text = json_text[3:] + if json_text.endswith("```"): + json_text = json_text[:-3] + json_text = json_text.strip() + + data = json5.loads(json_text) + story_text = data.get("text", "") + image_info = data.get("image", {}) + + # 确保图片信息完整 + if not isinstance(image_info, dict): + image_info = {} + + logger.info(f"成功生成说说：'{story_text}'") + logger.info(f"配图信息: {image_info}") + + return story_text, image_info + + except Exception as e: + logger.error(f"解析JSON失败: {e}, 原始响应: {response[:200]}") + # 降级处理：只返回文本，空配图信息 + return response, {} + else: + logger.error("生成说说内容失败") + return "", {} + + except Exception as e: + logger.error(f"生成说说内容时发生异常: {e}") + return "", {} """ 针对一条具体的说说内容生成评论。 """ diff --git a/src/plugins/built_in/maizone_refactored/services/image_service.py b/src/plugins/built_in/maizone_refactored/services/image_service.py index d83b246c6..ba6eeb9f5 100644 --- a/src/plugins/built_in/maizone_refactored/services/image_service.py +++ b/src/plugins/built_in/maizone_refactored/services/image_service.py @@ -31,18 +31,48 @@ class ImageService: """ self.get_config = get_config + async def generate_image_from_prompt(self, prompt: str, save_dir: str | None = None) -> tuple[bool, Path | None]: + """ + 直接使用提示词生成图片（硅基流动） + + :param prompt: 图片提示词（英文） + :param save_dir: 图片保存目录（None使用默认） + :return: (是否成功, 图片路径) + """ + try: + api_key = str(self.get_config("siliconflow.api_key", "")) + image_num = self.get_config("ai_image.image_number", 1) + + if not api_key: + logger.warning("硅基流动API未配置，跳过图片生成") + return False, None + + # 图片目录 + if save_dir: + image_dir = Path(save_dir) + else: + plugin_dir = Path(__file__).parent.parent + image_dir = plugin_dir / "images" + image_dir.mkdir(parents=True, exist_ok=True) + + logger.info(f"正在生成 {image_num} 张AI配图...") + success, img_path = await self._call_siliconflow_api(api_key, prompt, str(image_dir), image_num) + return success, img_path + + except Exception as e: + logger.error(f"生成AI配图时发生异常: {e}") + return False, None + async def generate_images_for_story(self, story: str) -> bool: """ - 根据说说内容，判断是否需要生成AI配图，并执行生成任务。 + 根据说说内容，判断是否需要生成AI配图，并执行生成任务（硅基流动）。 :param story: 说说内容。 :return: 图片是否成功生成（或不需要生成）。 """ try: - enable_ai_image = bool(self.get_config("send.enable_ai_image", False)) - api_key = str(self.get_config("models.siliconflow_apikey", "")) - image_dir = str(self.get_config("send.image_directory", "./data/plugins/maizone_refactored/images")) - image_num_raw = self.get_config("send.ai_image_number", 1) + api_key = str(self.get_config("siliconflow.api_key", "")) + image_num_raw = self.get_config("ai_image.image_number", 1) # 安全地处理图片数量配置，并限制在API允许的范围内 try: @@ -52,15 +82,14 @@ class ImageService: logger.warning(f"无效的图片数量配置: {image_num_raw}，使用默认值1") image_num = 1 - if not enable_ai_image: - return True # 未启用AI配图，视为成功 - if not api_key: - logger.error("启用了AI配图但未填写SiliconFlow API密钥") - return False + logger.warning("硅基流动API未配置，跳过图片生成") + return True - # 确保图片目录存在 - Path(image_dir).mkdir(parents=True, exist_ok=True) + # 图片目录（使用统一配置） + plugin_dir = Path(__file__).parent.parent + image_dir = plugin_dir / "images" + image_dir.mkdir(parents=True, exist_ok=True) # 生成图片提示词 image_prompt = await self._generate_image_prompt(story) @@ -69,7 +98,8 @@ class ImageService: return False logger.info(f"正在为说说生成 {image_num} 张AI配图...") - return await self._call_siliconflow_api(api_key, image_prompt, image_dir, image_num) + success, _ = await self._call_siliconflow_api(api_key, image_prompt, str(image_dir), image_num) + return success except Exception as e: logger.error(f"处理AI配图时发生异常: {e}") @@ -127,7 +157,7 @@ class ImageService: logger.error(f"生成图片提示词时发生异常: {e}") return "" - async def _call_siliconflow_api(self, api_key: str, image_prompt: str, image_dir: str, batch_size: int) -> bool: + async def _call_siliconflow_api(self, api_key: str, image_prompt: str, image_dir: str, batch_size: int) -> tuple[bool, Path | None]: """ 调用硅基流动（SiliconFlow）的API来生成图片。 @@ -135,7 +165,7 @@ class ImageService: :param image_prompt: 用于生成图片的提示词。 :param image_dir: 图片保存目录。 :param batch_size: 生成图片的数量（1-4）。 - :return: API调用是否成功。 + :return: (API调用是否成功, 第一张图片路径) """ url = "https://api.siliconflow.cn/v1/images/generations" headers = { @@ -175,12 +205,13 @@ class ImageService: error_text = await response.text() logger.error(f"生成图片出错，错误码[{response.status}]") logger.error(f"错误响应: {error_text}") - return False + return False, None json_data = await response.json() image_urls = [img["url"] for img in json_data["images"]] success_count = 0 + first_img_path = None # 下载并保存图片 for i, img_url in enumerate(image_urls): try: @@ -194,7 +225,7 @@ class ImageService: image = Image.open(BytesIO(img_data)) # 保存图片为PNG格式（确保兼容性） - filename = f"image_{i}.png" + filename = f"siliconflow_{i}.png" save_path = Path(image_dir) / filename # 转换为RGB模式如果必要（避免RGBA等模式的问题） @@ -206,21 +237,25 @@ class ImageService: image.save(save_path, format="PNG") logger.info(f"图片已保存至: {save_path}") success_count += 1 + + # 记录第一张图片路径 + if first_img_path is None: + first_img_path = save_path except Exception as e: logger.error(f"处理图片失败: {e!s}") continue except Exception as e: - logger.error(f"下载第{i+1}张图片失败: {e!s}") + logger.error(f"下载图片失败: {e!s}") continue - # 只要至少有一张图片成功就返回True - return success_count > 0 + # 至少有一张图片成功就返回True + return success_count > 0, first_img_path except Exception as e: logger.error(f"调用AI生图API时发生异常: {e}") - return False + return False, None def _encode_image_to_base64(self, img: Image.Image) -> str: """ diff --git a/src/plugins/built_in/maizone_refactored/services/novelai_service.py b/src/plugins/built_in/maizone_refactored/services/novelai_service.py new file mode 100644 index 000000000..58c3168cf --- /dev/null +++ b/src/plugins/built_in/maizone_refactored/services/novelai_service.py @@ -0,0 +1,286 @@ +""" +NovelAI图片生成服务 - 空间插件专用 +独立实现，不依赖其他插件 +""" +import asyncio +import base64 +import random +import uuid +import zipfile +import io +from pathlib import Path +from typing import Optional + +import aiohttp +from PIL import Image + +from src.common.logger import get_logger + +logger = get_logger("MaiZone.NovelAIService") + + +class MaiZoneNovelAIService: + """空间插件的NovelAI图片生成服务（独立实现）""" + + def __init__(self, get_config): + self.get_config = get_config + + # NovelAI配置 + self.api_key = self.get_config("novelai.api_key", "") + self.base_url = "https://image.novelai.net/ai/generate-image" + self.model = "nai-diffusion-4-5-full" + + # 代理配置 + proxy_host = self.get_config("novelai.proxy_host", "") + proxy_port = self.get_config("novelai.proxy_port", 0) + self.proxy = f"http://{proxy_host}:{proxy_port}" if proxy_host and proxy_port else "" + + # 生成参数 + self.steps = 28 + self.scale = 5.0 + self.sampler = "k_euler" + self.noise_schedule = "karras" + + # 角色提示词（当LLM决定包含角色时使用） + self.character_prompt = self.get_config("novelai.character_prompt", "") + self.base_negative_prompt = self.get_config("novelai.base_negative_prompt", "nsfw, nude, explicit, sexual content, lowres, bad anatomy, bad hands") + + # 图片保存目录（使用统一配置） + plugin_dir = Path(__file__).parent.parent + self.image_dir = plugin_dir / "images" + self.image_dir.mkdir(parents=True, exist_ok=True) + + if self.api_key: + logger.info(f"NovelAI图片生成已配置，模型: {self.model}") + + def is_available(self) -> bool: + """检查NovelAI服务是否可用""" + return bool(self.api_key) + + async def generate_image_from_prompt_data( + self, + prompt: str, + negative_prompt: Optional[str] = None, + include_character: bool = False, + width: int = 1024, + height: int = 1024 + ) -> tuple[bool, Optional[Path], str]: + """根据提示词生成图片 + + Args: + prompt: NovelAI格式的英文提示词 + negative_prompt: LLM生成的负面提示词（可选） + include_character: 是否包含角色形象 + width: 图片宽度 + height: 图片高度 + + Returns: + (是否成功, 图片路径, 消息) + """ + if not self.api_key: + return False, None, "NovelAI API Key未配置" + + try: + # 处理角色提示词 + final_prompt = prompt + if include_character and self.character_prompt: + final_prompt = f"{self.character_prompt}, {prompt}" + logger.info(f"包含角色形象，添加角色提示词") + + # 合并负面提示词 + final_negative = self.base_negative_prompt + if negative_prompt: + if final_negative: + final_negative = f"{final_negative}, {negative_prompt}" + else: + final_negative = negative_prompt + + logger.info(f"🎨 开始生成图片...") + logger.info(f" 尺寸: {width}x{height}") + logger.info(f" 正面提示词: {final_prompt[:100]}...") + logger.info(f" 负面提示词: {final_negative[:100]}...") + + # 构建请求payload + payload = self._build_payload(final_prompt, final_negative, width, height) + + # 发送请求 + image_data = await self._call_novelai_api(payload) + if not image_data: + return False, None, "API请求失败" + + # 保存图片 + image_path = await self._save_image(image_data) + if not image_path: + return False, None, "图片保存失败" + + logger.info(f"✅ 图片生成成功: {image_path}") + return True, image_path, "生成成功" + + except Exception as e: + logger.error(f"生成图片时出错: {e}", exc_info=True) + return False, None, f"生成失败: {str(e)}" + + def _build_payload(self, prompt: str, negative_prompt: str, width: int, height: int) -> dict: + """构建NovelAI API请求payload""" + is_v4_model = "diffusion-4" in self.model + is_v3_model = "diffusion-3" in self.model + + parameters = { + "width": width, + "height": height, + "scale": self.scale, + "steps": self.steps, + "sampler": self.sampler, + "seed": random.randint(0, 9999999999), + "n_samples": 1, + "ucPreset": 0, + "qualityToggle": True, + "sm": False, + "sm_dyn": False, + "noise_schedule": self.noise_schedule if is_v4_model else "native", + } + + # V4.5模型使用新格式 + if is_v4_model: + parameters.update({ + "params_version": 3, + "cfg_rescale": 0, + "autoSmea": False, + "legacy": False, + "legacy_v3_extend": False, + "legacy_uc": False, + "add_original_image": True, + "controlnet_strength": 1, + "dynamic_thresholding": False, + "prefer_brownian": True, + "normalize_reference_strength_multiple": True, + "use_coords": True, + "inpaintImg2ImgStrength": 1, + "deliberate_euler_ancestral_bug": False, + "skip_cfg_above_sigma": None, + "characterPrompts": [], + "stream": "msgpack", + "v4_prompt": { + "caption": { + "base_caption": prompt, + "char_captions": [] + }, + "use_coords": True, + "use_order": True + }, + "v4_negative_prompt": { + "caption": { + "base_caption": negative_prompt, + "char_captions": [] + }, + "legacy_uc": False + }, + "negative_prompt": negative_prompt, + "reference_image_multiple": [], + "reference_information_extracted_multiple": [], + "reference_strength_multiple": [] + }) + # V3使用negative_prompt字段 + elif is_v3_model: + parameters["negative_prompt"] = negative_prompt + + payload = { + "input": prompt, + "model": self.model, + "action": "generate", + "parameters": parameters + } + + # V4.5需要额外字段 + if is_v4_model: + payload["use_new_shared_trial"] = True + + return payload + + async def _call_novelai_api(self, payload: dict) -> Optional[bytes]: + """调用NovelAI API""" + headers = { + "Authorization": f"Bearer {self.api_key}", + "Content-Type": "application/json", + } + + connector = None + request_kwargs = { + "json": payload, + "headers": headers, + "timeout": aiohttp.ClientTimeout(total=120) + } + + if self.proxy: + request_kwargs["proxy"] = self.proxy + connector = aiohttp.TCPConnector() + logger.info(f"使用代理: {self.proxy}") + + try: + async with aiohttp.ClientSession(connector=connector) as session: + async with session.post(self.base_url, **request_kwargs) as resp: + if resp.status != 200: + error_text = await resp.text() + logger.error(f"API请求失败 ({resp.status}): {error_text[:200]}") + return None + + img_data = await resp.read() + logger.info(f"收到响应数据: {len(img_data)} bytes") + + # 检查是否是ZIP文件 + if img_data[:4] == b'PK\x03\x04': + logger.info("检测到ZIP格式，解压中...") + return self._extract_from_zip(img_data) + elif img_data[:4] == b'\x89PNG': + logger.info("检测到PNG格式") + return img_data + else: + logger.warning(f"未知文件格式，前4字节: {img_data[:4].hex()}") + return img_data + + except Exception as e: + logger.error(f"API调用失败: {e}", exc_info=True) + return None + + def _extract_from_zip(self, zip_data: bytes) -> Optional[bytes]: + """从ZIP中提取PNG""" + try: + with zipfile.ZipFile(io.BytesIO(zip_data)) as zf: + for filename in zf.namelist(): + if filename.lower().endswith('.png'): + img_data = zf.read(filename) + logger.info(f"从ZIP提取: {filename} ({len(img_data)} bytes)") + return img_data + logger.error("ZIP中未找到PNG文件") + return None + except Exception as e: + logger.error(f"解压ZIP失败: {e}") + return None + + async def _save_image(self, image_data: bytes) -> Optional[Path]: + """保存图片到本地""" + try: + filename = f"novelai_{uuid.uuid4().hex[:12]}.png" + filepath = self.image_dir / filename + + # 写入文件 + with open(filepath, "wb") as f: + f.write(image_data) + f.flush() + import os + os.fsync(f.fileno()) + + # 验证图片 + try: + with Image.open(filepath) as img: + img.verify() + with Image.open(filepath) as img: + logger.info(f"图片验证成功: {img.format} {img.size}") + except Exception as e: + logger.warning(f"图片验证失败: {e}") + + return filepath + + except Exception as e: + logger.error(f"保存图片失败: {e}") + return None diff --git a/src/plugins/built_in/maizone_refactored/services/qzone_service.py b/src/plugins/built_in/maizone_refactored/services/qzone_service.py index 6b05564f6..4bb3c75af 100644 --- a/src/plugins/built_in/maizone_refactored/services/qzone_service.py +++ b/src/plugins/built_in/maizone_refactored/services/qzone_service.py @@ -83,21 +83,93 @@ class QZoneService: return context async def send_feed(self, topic: str, stream_id: str | None) -> dict[str, Any]: - """发送一条说说""" + """发送一条说说（支持AI配图）""" cross_context = await self._get_cross_context() - story = await self.content_service.generate_story(topic, context=cross_context) - if not story: - return {"success": False, "message": "生成说说内容失败"} - - await self.image_service.generate_images_for_story(story) + + # 检查是否启用AI配图 + ai_image_enabled = self.get_config("ai_image.enable_ai_image", False) + provider = self.get_config("ai_image.provider", "siliconflow") + + image_path = None + + if ai_image_enabled: + # 启用AI配图：文本模型生成说说+图片提示词 + story, image_info = await self.content_service.generate_story_with_image_info(topic, context=cross_context) + if not story: + return {"success": False, "message": "生成说说内容失败"} + + # 根据provider调用对应的生图服务 + if provider == "novelai": + try: + from .novelai_service import MaiZoneNovelAIService + novelai_service = MaiZoneNovelAIService(self.get_config) + + if novelai_service.is_available(): + # 解析画幅 + aspect_ratio = image_info.get("aspect_ratio", "方图") + size_map = { + "方图": (1024, 1024), + "横图": (1216, 832), + "竖图": (832, 1216), + } + width, height = size_map.get(aspect_ratio, (1024, 1024)) + + logger.info(f"🎨 开始生成NovelAI配图...") + success, img_path, msg = await novelai_service.generate_image_from_prompt_data( + prompt=image_info.get("prompt", ""), + negative_prompt=image_info.get("negative_prompt"), + include_character=image_info.get("include_character", False), + width=width, + height=height + ) + + if success and img_path: + image_path = img_path + logger.info(f"✅ NovelAI配图生成成功") + else: + logger.warning(f"⚠️ NovelAI配图生成失败: {msg}") + else: + logger.warning("NovelAI服务不可用（未配置API Key）") + + except Exception as e: + logger.error(f"NovelAI配图生成出错: {e}", exc_info=True) + + elif provider == "siliconflow": + try: + # 调用硅基流动生成图片 + success, img_path = await self.image_service.generate_image_from_prompt( + prompt=image_info.get("prompt", ""), + save_dir=None # 使用默认images目录 + ) + if success and img_path: + image_path = img_path + logger.info(f"✅ 硅基流动配图生成成功") + else: + logger.warning(f"⚠️ 硅基流动配图生成失败") + except Exception as e: + logger.error(f"硅基流动配图生成出错: {e}", exc_info=True) + else: + # 不使用AI配图：只生成说说文本 + story = await self.content_service.generate_story(topic, context=cross_context) + if not story: + return {"success": False, "message": "生成说说内容失败"} qq_account = config_api.get_global_config("bot.qq_account", "") api_client = await self._get_api_client(qq_account, stream_id) if not api_client: return {"success": False, "message": "获取QZone API客户端失败"} - image_dir = self.get_config("send.image_directory") - images_bytes = self._load_local_images(image_dir) + # 加载图片 + images_bytes = [] + + # 使用AI生成的图片 + if image_path and image_path.exists(): + try: + with open(image_path, "rb") as f: + images_bytes.append(f.read()) + logger.info(f"添加AI配图到说说") + except Exception as e: + logger.error(f"读取AI配图失败: {e}") try: success, _ = await api_client["publish"](story, images_bytes) @@ -115,19 +187,16 @@ class QZoneService: if not story: return {"success": False, "message": "根据活动生成说说内容失败"} - await self.image_service.generate_images_for_story(story) + if self.get_config("send.enable_ai_image", False): + await self.image_service.generate_images_for_story(story) qq_account = config_api.get_global_config("bot.qq_account", "") - # 注意：定时任务通常在后台运行，没有特定的用户会话，因此 stream_id 为 None api_client = await self._get_api_client(qq_account, stream_id=None) if not api_client: return {"success": False, "message": "获取QZone API客户端失败"} - image_dir = self.get_config("send.image_directory") - images_bytes = self._load_local_images(image_dir) - try: - success, _ = await api_client["publish"](story, images_bytes) + success, _ = await api_client["publish"](story, []) if success: return {"success": True, "message": story} return {"success": False, "message": "发布说说至QQ空间失败"} @@ -434,7 +503,12 @@ class QZoneService: logger.debug(f"锁定待评论说说: {comment_key}") self.processing_comments.add(comment_key) try: - comment_text = await self.content_service.generate_comment(content, target_name, rt_con, images) + # 使用content_service生成评论（相当于回复好友的说说） + comment_text = await self.content_service.generate_comment_reply( + story_content=content or rt_con or "说说内容", + comment_content="", # 评论说说时没有评论内容 + commenter_name=target_name + ) if comment_text: success = await api_client["comment"](target_qq, fid, comment_text) if success: @@ -465,61 +539,6 @@ class QZoneService: return result - def _load_local_images(self, image_dir: str) -> list[bytes]: - """随机加载本地图片（不删除文件）""" - images = [] - if not image_dir or not os.path.exists(image_dir): - logger.warning(f"图片目录不存在或未配置: {image_dir}") - return images - - try: - # 获取所有图片文件 - all_files = [ - f - for f in os.listdir(image_dir) - if os.path.isfile(os.path.join(image_dir, f)) - and f.lower().endswith((".jpg", ".jpeg", ".png", ".gif", ".bmp")) - ] - - if not all_files: - logger.warning(f"图片目录中没有找到图片文件: {image_dir}") - return images - - # 检查是否启用配图 - enable_image = bool(self.get_config("send.enable_image", False)) - if not enable_image: - logger.info("说说配图功能已关闭") - return images - - # 根据配置选择图片数量 - config_image_number = self.get_config("send.image_number", 1) - try: - config_image_number = int(config_image_number) - except (ValueError, TypeError): - config_image_number = 1 - logger.warning("配置项 image_number 值无效，使用默认值 1") - - max_images = min(min(config_image_number, 9), len(all_files)) # 最多9张，最少1张 - selected_count = max(1, max_images) # 确保至少选择1张 - selected_files = random.sample(all_files, selected_count) - - logger.info(f"从 {len(all_files)} 张图片中随机选择了 {selected_count} 张配图") - - for filename in selected_files: - full_path = os.path.join(image_dir, filename) - try: - with open(full_path, "rb") as f: - image_data = f.read() - images.append(image_data) - logger.info(f"加载图片: {filename} ({len(image_data)} bytes)") - except Exception as e: - logger.error(f"加载图片 {filename} 失败: {e}") - - return images - except Exception as e: - logger.error(f"加载本地图片失败: {e}") - return [] - def _generate_gtk(self, skey: str) -> str: hash_val = 5381 for char in skey: