app: description: Workflow，基于Doubao Seedream 4.5 icon: 🤖 icon_background: '#FFEAD5' icon_type: emoji mode: workflow name: 文生图workflow use_icon_as_answer_icon: false dependencies: - current_identifier: null type: marketplace value: marketplace_plugin_unique_identifier: langgenius/volcengine_maas:0.0.46@cbdbb9440236d4e83ee6a14566d42a75ab478abf47127c56d1f05642e4c60baf version: null - current_identifier: null type: marketplace value: marketplace_plugin_unique_identifier: sawyer-shi/seedream_aigc:0.0.1@cb3174212b2e32038019fdbbba3c970f68116533ec294a30e6ebdb5af23a4662 version: null kind: app version: 0.6.0 workflow: conversation_variables: [] environment_variables: [] features: file_upload: allowed_file_extensions: - .JPG - .JPEG - .PNG - .GIF - .WEBP - .SVG allowed_file_types: - image allowed_file_upload_methods: - local_file - remote_url enabled: false fileUploadConfig: attachment_image_file_size_limit: 2 audio_file_size_limit: 50 batch_count_limit: 5 file_size_limit: 15 file_upload_limit: 20 image_file_batch_limit: 10 image_file_size_limit: 10 single_chunk_attachment_limit: 10 video_file_size_limit: 100 workflow_file_upload_limit: 10 image: enabled: false number_limits: 3 transfer_methods: - local_file - remote_url number_limits: 3 opening_statement: '' retriever_resource: enabled: true sensitive_word_avoidance: enabled: false speech_to_text: enabled: false suggested_questions: [] suggested_questions_after_answer: enabled: false text_to_speech: enabled: false language: '' voice: '' graph: edges: - data: isInLoop: false sourceType: start targetType: llm id: 1770860537607-source-1770860542237-target selected: false source: '1770860537607' sourceHandle: source target: '1770860542237' targetHandle: target type: custom zIndex: 0 - data: isInIteration: false isInLoop: false sourceType: llm targetType: end id: 1770860542237-source-1770906524488-target selected: false source: '1770860542237' sourceHandle: source target: '1770906524488' targetHandle: target type: custom zIndex: 0 - data: isInIteration: false isInLoop: false sourceType: llm targetType: tool id: 1770860542237-source-1772413887082-target source: '1770860542237' sourceHandle: source target: '1772413887082' targetHandle: target type: custom zIndex: 0 - data: isInLoop: false sourceType: tool targetType: end id: 1772413887082-source-1770906524488-target source: '1772413887082' sourceHandle: source target: '1770906524488' targetHandle: target type: custom zIndex: 0 nodes: - data: selected: false title: 开始 type: start variables: - default: '' hint: '' label: 图片生成要求 options: [] placeholder: '' required: true type: paragraph variable: query height: 109 id: '1770860537607' position: x: 120.48998334276632 y: 282 positionAbsolute: x: 120.48998334276632 y: 282 selected: false sourcePosition: right targetPosition: left type: custom width: 242 - data: context: enabled: false variable_selector: [] desc: '' model: completion_params: thinking: disabled mode: chat name: Doubao-Seed-2.0-lite provider: langgenius/volcengine_maas/volcengine_maas prompt_template: - id: 30ca449a-8f74-411d-aac2-a8dfca5f7c20 role: system text: '你是一位专业的 AI 绘画提示词优化专家，专门优化适用于表情包图像生成模型的提示词。 你的任务是： 将用户简单、模糊或口语化的描述，优化为清晰、具体、具有画面感、适合表情包图像生成模型的高质量提示词。 🦾 优化规则 1️⃣ 使用自然语言完整描述画面 避免堆砌关键词，使用流畅中文表达。 2️⃣ 必须补充以下要素（若用户未提供）： 主体特征（外貌、服装、表情、动作） 场景环境（地点、时间、天气） 光线效果（柔光、夕阳、逆光、霓虹灯等） 画面氛围（温暖、唯美、科技感、史诗感等） 画面清晰度与细节（高清、细节丰富、真实质感等） 3️⃣ 画面增强建议（智能补充） 可以合理补充： 镜头视角（近景、特写、广角、俯拍等） 构图方式（居中构图、电影构图） 质感细节（皮肤纹理、布料质感、金属反光等） 风格说明（写实摄影风格、二次元插画风格、赛博朋克风格等） 🚫 禁止事项 不要解释 不要分点 不要加引号 不要输出多个版本 只输出优化后的完整提示词 🔥 示例 用户输入： 未来城市 优化输出： 一座充满未来科技感的城市，高耸入云的玻璃与金属建筑，空中飞行汽车穿梭在霓虹灯光照亮的街道上，夜晚场景，蓝紫色霓虹灯光映射在潮湿的地面上，画面具有强烈的赛博朋克氛围，广角视角，细节丰富，高清画质，电影级光影效果 现在，请优化以下用户提供的描述：{{#1770860537607.query#}}' - id: 8a923e7a-8934-4b9a-ba3f-4e80d37710de role: user text: '' reasoning_format: tagged selected: false structured_output_enabled: false title: 优化提示词 type: llm vision: enabled: false height: 88 id: '1770860542237' position: x: 407.1277995859348 y: 303 positionAbsolute: x: 407.1277995859348 y: 303 selected: true sourcePosition: right targetPosition: left type: custom width: 242 - data: outputs: - value_selector: - '1770860542237' - text value_type: string variable: text - value_selector: - '1772413887082' - files value_type: array[file] variable: files selected: false title: 结束 type: end height: 114 id: '1770906524488' position: x: 1042.2803364774247 y: 303 positionAbsolute: x: 1042.2803364774247 y: 303 selected: false sourcePosition: right targetPosition: left type: custom width: 242 - data: is_team_authorization: true paramSchemas: - auto_generate: null default: null form: llm human_description: en_US: Text description of the image you want to generate ja_JP: Text description of the image you want to generate pt_BR: Text description of the image you want to generate zh_Hans: 您想要生成的图像的文本描述 label: en_US: Prompt ja_JP: Prompt pt_BR: Prompt zh_Hans: 提示词 llm_description: Text description of the image to generate max: null min: null name: prompt options: [] placeholder: null precision: null required: true scope: null template: null type: string - auto_generate: null default: 2048x2048 form: form human_description: en_US: Size of the generated image ja_JP: Size of the generated image pt_BR: Size of the generated image zh_Hans: 生成图像的尺寸 label: en_US: Image Size ja_JP: Image Size pt_BR: Image Size zh_Hans: 图像尺寸 llm_description: Size of the generated image max: null min: null name: size options: - icon: '' label: en_US: 1:1 (2048x2048) ja_JP: 1:1 (2048x2048) pt_BR: 1:1 (2048x2048) zh_Hans: 1:1 (2048x2048) value: 2048x2048 - icon: '' label: en_US: 4:3 (2304x1728) ja_JP: 4:3 (2304x1728) pt_BR: 4:3 (2304x1728) zh_Hans: 4:3 (2304x1728) value: 2304x1728 - icon: '' label: en_US: 3:4 (1728x2304) ja_JP: 3:4 (1728x2304) pt_BR: 3:4 (1728x2304) zh_Hans: 3:4 (1728x2304) value: 1728x2304 - icon: '' label: en_US: 16:9 (2560x1440) ja_JP: 16:9 (2560x1440) pt_BR: 16:9 (2560x1440) zh_Hans: 16:9 (2560x1440) value: 2560x1440 - icon: '' label: en_US: 9:16 (1440x2560) ja_JP: 9:16 (1440x2560) pt_BR: 9:16 (1440x2560) zh_Hans: 9:16 (1440x2560) value: 1440x2560 - icon: '' label: en_US: 3:2 (2496x1664) ja_JP: 3:2 (2496x1664) pt_BR: 3:2 (2496x1664) zh_Hans: 3:2 (2496x1664) value: 2496x1664 - icon: '' label: en_US: 2:3 (1664x2496) ja_JP: 2:3 (1664x2496) pt_BR: 2:3 (1664x2496) zh_Hans: 2:3 (1664x2496) value: 1664x2496 - icon: '' label: en_US: 21:9 (3024x1296) ja_JP: 21:9 (3024x1296) pt_BR: 21:9 (3024x1296) zh_Hans: 21:9 (3024x1296) value: 3024x1296 placeholder: null precision: null required: false scope: null template: null type: select - auto_generate: null default: 'true' form: form human_description: en_US: Whether to add 'AI Generated' watermark to the image ja_JP: Whether to add 'AI Generated' watermark to the image pt_BR: Whether to add 'AI Generated' watermark to the image zh_Hans: 是否在图像上添加'AI生成'水印 label: en_US: Watermark ja_JP: Watermark pt_BR: Watermark zh_Hans: 水印 llm_description: Whether to add 'AI Generated' watermark to the image max: null min: null name: watermark options: - icon: '' label: en_US: Enabled ja_JP: Enabled pt_BR: Enabled zh_Hans: 启用 value: 'true' - icon: '' label: en_US: Disabled ja_JP: Disabled pt_BR: Disabled zh_Hans: 禁用 value: 'false' placeholder: null precision: null required: false scope: null template: null type: select - auto_generate: null default: doubao-seedream-4-5-251128 form: form human_description: en_US: Choose the Seedream model version to use ja_JP: Choose the Seedream model version to use pt_BR: Choose the Seedream model version to use zh_Hans: 选择要使用的Seedream模型版本 label: en_US: Model Version ja_JP: Model Version pt_BR: Model Version zh_Hans: 模型版本 llm_description: Choose the Seedream model version to use max: null min: null name: model options: - icon: '' label: en_US: Seedream4.0 ja_JP: Seedream4.0 pt_BR: Seedream4.0 zh_Hans: Seedream4.0 value: doubao-seedream-4-0-250828 - icon: '' label: en_US: Seedream4.5 ja_JP: Seedream4.5 pt_BR: Seedream4.5 zh_Hans: Seedream4.5 value: doubao-seedream-4-5-251128 - icon: '' label: en_US: Seedream5.0 Lite ja_JP: Seedream5.0 Lite pt_BR: Seedream5.0 Lite zh_Hans: Seedream5.0 Lite value: doubao-seedream-5-0-260128 placeholder: null precision: null required: false scope: null template: null type: select params: model: '' prompt: '' size: '' watermark: '' plugin_id: sawyer-shi/seedream_aigc plugin_unique_identifier: sawyer-shi/seedream_aigc:0.0.1@cb3174212b2e32038019fdbbba3c970f68116533ec294a30e6ebdb5af23a4662 provider_icon: /console/api/workspaces/current/plugin/icon?tenant_id=c01909a5-16ac-4f4f-86f2-bf3c5643f5a6&filename=9638639a259e524d8a12d8fa29d692c7b226cc88124ff4fb1eb2d31d0c9f88d3.svg provider_id: sawyer-shi/seedream_aigc/seedream_aigc provider_name: sawyer-shi/seedream_aigc/seedream_aigc provider_type: builtin selected: false title: 生成图片 tool_configurations: model: type: constant value: doubao-seedream-4-5-251128 size: type: constant value: 2304x1728 watermark: type: constant value: 'false' tool_description: 使用Seedream模型根据文本描述生成图像 tool_label: Seedream-文生图 tool_name: text2image tool_node_version: '2' tool_parameters: prompt: type: mixed value: '{{#1770860542237.text#}}' type: tool height: 140 id: '1772413887082' position: x: 724.3961460301044 y: 363.17781638938254 positionAbsolute: x: 724.3961460301044 y: 363.17781638938254 selected: false sourcePosition: right targetPosition: left type: custom width: 242 viewport: x: 129.28736721338242 y: 132.27871402175327 zoom: 0.7450591277173519 rag_pipeline_variables: []