單格構圖
令每格 AI 漫畫分鏡都有清晰故事用途
規劃一個 AI 漫畫分鏡，定好故事節點、鏡頭距離同角色位置。喺建立完整序列之前先檢查構圖。
模型
呢個創作器會生成靜態圖片。漫畫同影片請繼續用連結工具；研究策略唔係可選生產模式。
圖片記錄
Google Vertex AI · gemini-3.1-flash-image · · 1280 × 859 px
原始生成提示詞
Use case: photorealistic-natural / product-mockup. Convincing natural editorial PHOTOGRAPH at an adult artist's clean drawing table. Supplied image1 is the original character identity sheet; image2 is the original six-panel greenhouse story. Four separate medium matte landscape cards lie in a clean two-by-two arrangement on the table. Their artwork uses the SAME original adult botanist in teal jacket and coral scarf, same mint-green one-antenna robot, same greenhouse and terra-cotta pot. Show four distinct useful framings from the supplied story: wide greenhouse establishing view, medium pot-on-bench action, close-up seed-and-hands detail, and medium shared watering action. Cards have generous blank ivory borders; all four are fully inside frame and none overlap. A smaller character-reference sheet from image1 sits just behind the cards, partly visible. Exactly one relaxed realistic adult hand rests at the edge without covering the art. Natural ink/watercolor illustration stays on paper; room, wooden table and skin are photographic. No writing, numbers, arrows, logos, app UI or made-up test results. The finished framing alternatives dominate 80 percent of frame, subtle pencil and linen details only. Landscape 3:2, almost overhead.
查看完整作品規劃具體結果
一位植物學家同一個機械人一齊準備一個花盆
一位成年植物學家將一個赤陶花盆放到溫室長凳上，而一個細小薄荷機械人喺旁邊等候。呢格需要展示動作同每個角色嘅作用，而唔依賴字幕。
要準備啲乜
- 原創成年植物學家同細小薄荷機械人嘅已授權身份參考。
- 一句話動作簡述同目前服裝備註。
- 簡單擺位草圖，或者清楚寫明左右安排。
圖片記錄
Google Vertex AI · gemini-3.1-flash-image · · 1280 × 859 px
原始生成提示詞
Use case: illustration-story. Make ONE original finished comic page in a clean three-column by two-row grid, exactly SIX equally sized panels, narrow even ivory gutters and complete outer margins. The provided image is the character identity and wardrobe reference, not a page to copy. Preserve its adult botanist with warm brown skin, short dark curly hair, teal jacket, coral scarf, sand trousers, brown boots, and round mint helper robot with two dark eyes and exactly one short antenna. Quiet elegant ink-and-watercolor comic style, teal/coral/sage/ochre palette. Tell a very simple readable rooftop greenhouse planting story: panel1 wide view botanist and robot arrive at the greenhouse carrying a small terra-cotta pot; panel2 medium view the botanist places the pot on the wooden bench; panel3 close view gloved adult hands holding a seed above the pot; panel4 medium view botanist and robot water the pot with a small cream watering can; panel5 close view botanist and robot look at the tiny seedling; panel6 wide view both stand by the finished row of three potted seedlings in afternoon light. All people are adults; each scene has one botanist and one robot unless only hands are framed. The pot remains terra-cotta, the greenhouse stays structurally coherent, identity and outfit remain recognizable. No writing, numbers, logos, speech balloons, captions, lettering, illegible marks, third-party characters, UI, photorealistic environment or claims of tested consistency. Landscape 3:2.
查看完整作品揀一個能講清交接動作嘅構圖
中景可以同時見到相關嘅手、機械人同花盆。太近會睇唔到邊個喺做動作，太闊又可能失去重要手勢。
將每個身份綁定到角色
要分開指出植物學家嘅動作同機械人嘅位置，包括外觀同相對比例。唔好因為其中一個身份似樣，就直接接受成張圖。
預留最終頁面空間
喺接受構圖前，先規劃分鏡裁切同任何文字區域。一張可用嘅獨立圖片，放入頁面版面時都可能會太擠。
成功嘅分鏡格應該清晰傳達一個節拍。當主體、動作同關係已經睇得明，吸引嘅細節先至重要。
一個實際可行嘅起點
寫一個可見嘅故事節點
描述讀者喺呢一格入面見到乜，而唔係總結成個故事。要指出主體、動作同重要物件。
揀定構圖同角色位置
決定鏡頭需要幾多場景資訊，同角色應該出現喺邊度。如果你嘅後期工作流程會加文字，就要預留位置。
喺預定閱讀尺寸檢查
檢查輪廓、視線、手部、道具位置同視覺層次。接受大預覽之前，應以整頁一部分去審視分鏡格。
要檢查啲乜
圖片記錄
Google Vertex AI · gemini-3.1-flash-image · · 1280 × 859 px
原始生成提示詞
Use case: photorealistic-natural / product-mockup. Convincing natural editorial PHOTOGRAPH at an adult artist's clean drawing table. Supplied image1 is the original character identity sheet; image2 is the original six-panel greenhouse story. Four separate medium matte landscape cards lie in a clean two-by-two arrangement on the table. Their artwork uses the SAME original adult botanist in teal jacket and coral scarf, same mint-green one-antenna robot, same greenhouse and terra-cotta pot. Show four distinct useful framings from the supplied story: wide greenhouse establishing view, medium pot-on-bench action, close-up seed-and-hands detail, and medium shared watering action. Cards have generous blank ivory borders; all four are fully inside frame and none overlap. A smaller character-reference sheet from image1 sits just behind the cards, partly visible. Exactly one relaxed realistic adult hand rests at the edge without covering the art. Natural ink/watercolor illustration stays on paper; room, wooden table and skin are photographic. No writing, numbers, arrows, logos, app UI or made-up test results. The finished framing alternatives dominate 80 percent of frame, subtle pencil and linen details only. Landscape 3:2, almost overhead.
查看完整作品研究方向
工作流程背後嘅研究
將每個參考對應到其區域
我哋正探索點樣令多個身份保持同預期位置連結。關於區域身份控制嘅公開研究可以提供參考，但唔代表每個供應商都已推出相關控制。
捉到睇落合理但其實錯嘅動作
一格畫面可以睇落好精緻，但實際上調轉咗交接次序或者多咗一個人。審核時應將故事一致性同角色數量，與外觀表現分開衡量。
修復最細失敗範圍
如果有一隻袖口或者手出錯，有針對性修補可能可以保留好構圖。但評估時亦要檢查未編輯區域有冇意外改動。
研究方向
視覺審核級聯
邊啲檢查可以及早發現身份或故事錯誤，邊啲就需要再仔細睇？
我哋會點樣評估: 追蹤漏判嚴重錯誤同誤拒分鏡，連同審核成本同延遲。
研究方向
定向角色修復
可唔可以只修正一個錯誤角色細節，同時保留已通過嘅場景？
我哋會點樣評估: 每次提議修補後，都要檢查編輯區、周邊像素同故事內容。
研究方向
多角色身份
喺互動過程中，每個角色都可唔可以保持正確面容、衣著、比例同位置？
我哋會點樣評估: 檢查每個鏡頭入面身份同位置嘅對應、角色數量同相對大小。
了解界線
- 文字簡述無法保證姿勢、數量或擺位完全準確。
- 精確版面或地區控制，取決於所選工具實際提供咩功能。
- 呢個示範規劃案例唔係對生成模型嘅量化比較。
初步研究只會為呢啲問題提供參考；並唔代表 CyaniModel 嘅結果。
常見問題
呢個同直接生成成套漫畫有咩分別？
呢個工作流程集中處理單一分鏡同其構圖。連結嘅漫畫工具提供可用嘅創作工作流程；完整序列亦需要節奏、轉場同連貫性檢查。
分鏡提示詞要寫到幾詳細？
描述畫面可見嘅節奏、主體同少量對故事最重要嘅細節。避免喺一個分鏡簡介入面塞入連串動作。
可以精準擺放兩個角色嗎？
講明預定排列方式，並使用任何受支援嘅構圖參考。之後再檢查輸出。單靠描述唔保證精確座標或者正確身份綁定。
只係一個錯誤，需唔需要重生整格？
比較可用嘅修正方法。局部編輯可能可以保留已接受嘅構圖，但仍然要檢查編輯範圍內外。
繼續你嘅故事
要令一格入面嘅動作同關係喺閱讀尺寸下都睇得明。
繼續喺 LlamaGen 入面查看可用工具、模型選項、帳戶要求同積分，再進行生成。