{ "format": "mosael-workflow", "version": 1, "workflow_revision": 1, "name": "Fabric into applications and a spec sheet", "description": "From one fabric photo and its specs, plan the products it genuinely suits (up to 12), render each one in a real space, and produce a one-page proposal you can send to a client. The spec sheet only restates the numbers you provide; anything missing is marked as needing mill confirmation. Each application is one paid image generation.", "graph_hash": "7e53f82465fceaa8ba511808b21968d9ae038868394fc1383cc4b7dc1ec3bd67", "graph": { "meta": { "template_id": "fabric_lookbook", "template_version": 3, "source": "official" }, "nodes": [ { "id": "start", "type": "start", "name": "Fabric specs", "position": { "x": 40, "y": 260 }, "config": { "params": { "fabric_name": "", "composition": "", "weight_gsm": "", "width_cm": "", "hand_feel": "", "target_client": "家纺采购 / 服装品牌", "application_count": 4 }, "required_params": [ "fabric_name" ] } }, { "id": "fabric_photo", "type": "asset", "name": "Pick the fabric photo", "position": { "x": 330, "y": 260 }, "config": { "asset_id": "" } }, { "id": "fabric_plan", "type": "llm", "name": "Plan the applications and the spec sheet", "position": { "x": 650, "y": 260 }, "config": { "profile_id": "", "model": "", "preset": "precise", "system": "你是面料商的技术销售和陈列企划。客户给你一块面料的参数，你要做两件事：\n\n1. 规划几种这块料**真的适合**的应用（家纺、服装、软装等），每种给一张成品效果图的英文提示词，\n 最多 12 种。\n 效果图要把成品放在真实空间里，让人一眼看出垂坠感、厚度和纹理，不是平铺特写。\n2. 写一页规格卡。\n\n硬性要求：\n- 规格卡**只能复述用户给出的参数**。成分、克重、幅宽、缩率、色牢度这些是要负责任的数字，\n 用户没给就不要写；确实需要但没有的，写「需与工厂确认」。\n- 不要承诺任何认证、检测结论或环保资质。\n- image_prompt 用英文，不要写机位参数，不要在画面里生成文字或水印。\n- 你**看不到**那块面料的图，所以不要描述它的花型和颜色细节——那由参考图保证。\n\n只输出符合 JSON Schema 的对象。", "prompt": "面料名称：{{start.fabric_name}}\n成分：{{start.composition}}\n克重：{{start.weight_gsm}}\n幅宽：{{start.width_cm}}\n手感与垂坠：{{start.hand_feel}}\n客户类型：{{start.target_client}}\n要几种应用：{{start.application_count}}\n\n请输出应用规划与规格卡。没给的参数不要编。", "response_format": "json_schema", "json_schema_name": "fabric_lookbook_plan", "json_schema": { "type": "object", "properties": { "spec_markdown": { "type": "string", "description": "规格卡正文,Markdown,中文;只写用户给出的参数,不要编造" }, "applications": { "type": "array", "items": { "type": "object", "properties": { "product_type": { "type": "string", "description": "做成什么,中文,如「窗帘」「单人沙发」「长袖衬衫」" }, "why_it_suits": { "type": "string", "description": "为什么这块料适合做它,中文,一句话" }, "image_prompt": { "type": "string", "description": "完整出图提示词,英文:成品在真实空间里的样子" } }, "required": [ "product_type", "why_it_suits", "image_prompt" ], "additionalProperties": false }, "minItems": 1, "maxItems": 12 }, "applications_markdown": { "type": "string", "description": "给客户看的应用清单,Markdown 无序列表,每种一行:「- **做成什么**:为什么这块料适合做它」" }, "care_notes": { "type": "string", "description": "养护与工艺提示,中文;不确定的写「需与工厂确认」" } }, "required": [ "spec_markdown", "applications", "applications_markdown", "care_notes" ], "additionalProperties": false }, "json_schema_strict": "true", "temperature": 0.4, "max_tokens": 8000 } }, { "id": "render_applications", "type": "loop_foreach", "name": "Render each application", "position": { "x": 970, "y": 260 }, "config": { "items": "{{fabric_plan.json.applications}}", "inputs": { "fabric_asset_id": "{{fabric_photo.asset_id}}", "fabric_name": "{{start.fabric_name}}" }, "body": { "nodes": [ { "id": "application_shot", "type": "ai_generate", "name": "Render this application", "position": { "x": 80, "y": 140 }, "config": { "provider": "", "provider_profile_id": "", "model": "", "kind": "image", "prompt": "{{loop.item.image_prompt}} The reference image is the actual fabric, photographed flat. Reproduce its weave, texture, colour, sheen and print scale EXACTLY on the finished product; do not restyle or recolour it. Photorealistic interior or product photography, natural light, no text, no watermark.", "negative_prompt": "different fabric, altered weave, changed colour, distorted pattern scale, text, watermark, plastic looking material", "parameters": {}, "source_assets": [ "{{input.fabric_asset_id}}:reference_image" ] } }, { "id": "tag_shot", "type": "asset_tag", "name": "Tag it with the fabric", "position": { "x": 400, "y": 140 }, "config": { "asset_ids": "", "tags": "面料提案,{{input.fabric_name}}", "mode": "add" }, "inputs": [ "asset_ids" ] } ], "edges": [ { "id": "shot_tag", "source": "application_shot", "target": "tag_shot" }, { "id": "d-application_shot-asset_id-tag_shot-asset_ids", "source": "application_shot", "target": "tag_shot", "kind": "data", "source_output": "asset_id", "target_input": "asset_ids" } ] }, "output": "{{application_shot.asset_id}}", "concurrency": 2, "max_items": "{{start.application_count}}", "on_item_error": "skip" } }, { "id": "spec_note", "type": "note_create", "name": "Write the spec sheet to send", "position": { "x": 1290, "y": 260 }, "config": { "title": "{{start.fabric_name}} · 规格与应用提案", "markdown": "{{fabric_plan.json.spec_markdown}}\n\n## 适合做什么\n\n{{fabric_plan.json.applications_markdown}}\n\n## 养护与工艺\n\n{{fabric_plan.json.care_notes}}\n\n---\n\n效果图为 AI 依据本面料实拍图生成,用于沟通版型与观感;**成分、克重、幅宽、色牢度以工厂实测为准**。\n", "tags": "面料提案" } }, { "id": "done_notice", "type": "notify", "name": "Proposal ready", "position": { "x": 1610, "y": 260 }, "config": { "title": "面料提案已生成", "body": "{{start.fabric_name}} 已出 {{render_applications.count}} 张应用效果图,规格页已存进笔记。\n{{render_applications.failure_note}}" } }, { "id": "output", "type": "output", "name": "Hand over the renders and the spec sheet", "position": { "x": 1930, "y": 260 }, "config": { "values": { "fabric_asset_id": "{{fabric_photo.asset_id}}", "render_asset_ids": "{{render_applications.results}}", "render_count": "{{render_applications.count}}", "plan": "{{fabric_plan.json}}", "spec_note_id": "{{spec_note.note_id}}" } } } ], "edges": [ { "id": "start_photo", "source": "start", "target": "fabric_photo" }, { "id": "start_plan", "source": "start", "target": "fabric_plan" }, { "id": "photo_render", "source": "fabric_photo", "target": "render_applications" }, { "id": "plan_render", "source": "fabric_plan", "target": "render_applications" }, { "id": "plan_note", "source": "fabric_plan", "target": "spec_note" }, { "id": "render_notice", "source": "render_applications", "target": "done_notice" }, { "id": "note_notice", "source": "spec_note", "target": "done_notice" }, { "id": "notice_output", "source": "done_notice", "target": "output" } ] } }