以参考为主导的图像创作
以一张图片作为新视觉草稿的起点
使用授权来源规划一次图生图转换。先决定保留哪些结构、要改哪些内容，以及如何审核生成草稿。
模型
这个创作工具生成的是静态图像。漫画和视频请继续使用链接中的工具；研究策略并不是可选的生产模式。
图片记录
Google Vertex AI · gemini-3.1-flash-image · · 1280 × 859 px
原始生成提示词
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.
查看完整作品规划具体结果
从温室草图到视觉初稿
用原创构图草图来规划温室场景。保留关键布局，同时探索新的视觉方向。
需要准备什么
- 经授权的草图，主体位置清晰。
- 说明期望视觉方向及需要保留结构的简要说明。
图片记录
Google Vertex AI · gemini-3.1-flash-image · · 1280 × 859 px
原始生成提示词
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.
查看完整作品用草图来确定构图
说明哪些主体和物体位置最重要，不要把每一处草图线条都当成成品细节。
说明预期修改
选择明确的视觉方向，并指出新图片需要说明清楚的细节。
检查故事信息
确认结果是否仍能说明预期动作，以及主体之间的关系。
当来源图的用途明确时，它能让说明更有帮助。审核结果时应对照这个用途，而不是期待每个属性都会自动迁移。
实用的起点
选择来源及其用途
判断这张图提供的是身份、构图、风格，还是其他参考。请使用你有权分享的素材。
定义变化目标
说明哪些内容应该改变，以及哪些特征必须保留。避免互相冲突的参考或含糊指令。
将结果与任务对比
把源图和输出一起检查。以预期展示尺寸核对结构、身份、要求的修改和错误。
检查什么
图片记录
Google Vertex AI · gemini-3.1-flash-image · · 1280 × 859 px
原始生成提示词
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
工作流背后的研究
按用途选择参考图
我们正在探索，明确匹配的身份、视角和构图参考，是否能减少无关或冲突的视觉信息。
衡量源图原本要保留的内容
身份、构图和风格是不同的评估问题。有效的对比应说明源图原本是想引导哪一项属性。
研究方向
角色一致性基准
在镜头、姿势、服装和场景变化下，角色的可识别性有多稳定？
我们会如何评估: 分别评估身份、服装、角色数量、故事一致性和每个已接受分镜的总成本。
研究方向
自适应参考选择
哪种身份、全身、服装或镜头视角参考更适合特定镜头？
我们会如何评估: 使用相同的故事和验收规则，对比固定参考集与镜头匹配集。
了解边界
- 图生图表现和参考控制会因所选模型与工具而异。
- 参考图并不能保证几何形状、身份或风格迁移完全一致。
这些问题参考了初步研究，但并不能证明 CyaniModel 的结果。
常见问题
图生图和局部照片编辑是一回事吗？
图生图工作流可能会重新解读整张图；局部编辑则针对特定改动。请查看你所选工具的控制方式和实际表现。
可以用草图代替照片吗？
受支持的参考工作流可能接受不同类型的图片。请明确草图用途，例如构图或姿势，并查看实际输出结果。
风格变化后能保证还是同一个角色吗？
风格变化可能会影响决定角色身份的细节。请保留清晰的身份参考并对照结果；无法保证百分百原样保留。
继续你的故事
让源图片在新结果中承担明确作用。
继续在 LlamaGen 中查看可用工具、模型选择、账户要求和积分后再生成。