原创角色设定|三视图与四表情
角色简报生成正侧背与表情页,附服装配饰一致性检查
原创角色设定|三视图与四表情
角色简报生成正侧背与表情页,附服装配饰一致性检查
Showcase
Description
适合为插画、分镜、吉祥物设计准备角色参考的创作者。 提供:角色用途、年龄或物种、体型、服装、配饰、画风与避用项;有授权参考图可以同时提供。 处理:先建立比例、颜色、角色自身左右和背部结构锚点,再调用当前图像工具生成正面、侧面、背面及四种表情,逐项检查服装与配饰。 交付:实际二维设定图、角色锚点、提示词及一致性检查记录。图像可用于后续插画与建模沟通,不包含3D模型、绑定动画、可编辑分层或工业结构。 使用:发送简报或参考图,确认角色描述与新增设定,生成后核对左右、背面及遮挡细节。有明显偏差时进行针对性修订,不能保证跨轮次绝对一致。 依赖:文字模型及支持生成/参考图编辑的图像工具。偏好GPT与GPT Image 2时须以平台实际可选模型为准;本地使用内置image_gen完成四个虚构原创案例,工具未返回图像模型编号,不能宣称已指定Image 2。YouMind端未追加运行测试、未验证持久模型绑定。运行时平台模型消耗或第三方API费用不包含在199积分售价内。无图像工具/额度时会明确未出图,不以提示词冒充成图。 四张展示图为本地实际输出,未重绘证据。仍可能有衣褶、细小配饰和文字偏差,发布或精细制作前请人工核对。 展示说明:首张为独立技能头像与案例01实际输出的并排排版,用于横向缩略展示;不是新增案例,也未让生图模型重绘证据。其余三张对应案例02—04。
Recommended by
Dancang
Why we love this skill
Transforms character briefs into three-view and four-expression concept sheets for illustrations, storyboards, and modeling. It features verifiable character anchors, consistency checks, and targeted revisions to maintain accessory and clothing identity.
Related Skills
View all
ImagePet Cartoon Character Sheet
Turn an existing realistic depiction of your pet into a consistent, expandable cartoon character sheet. Use it as a stable visual reference for creating stickers, memes, comics, or animations. Before using this Skill, prepare a pet profile with realistic reference images, fur color, body type, distinctive features, accessories, and other details. The generated result will aim to preserve the character’s recognizability and maintain consistent details. The final result is a multi-view character sheet featuring front, side, and back views, a full-body chibi view, different emotional expressions, and signature accessories such as collars or tags. It also preserves the relationships between the primary and secondary colors. You can choose a 2D flat cartoon style, suitable for memes, stickers, and comics, or a 3D cartoon rendering style, suitable for animation, games, or 3D merchandise. If no style is specified, 2D is used by default. The generated cartoon character is also recorded in the pet profile, making it easier to maintain the same art style, fur colors, and accessory settings in future meme creation. This helps prevent character distortion or inconsistent styling from one creation to the next.
ImageIP Character Felt Turnaround
Give your favorite character a soft, cozy felt texture with visible wool fibers. Upload a character image or write a one-line character description to create front, 90° side, and back views of the same character. Existing characters can retain their facial features, color palette, clothing, and signature accessories. With no reference image, you can also start from text. You’ll receive: • A complete felt-style front, side, and back character turnaround. • A clear visual description of the character’s appearance for future use. • Reusable generation prompts for further edits and expansions. The process first organizes the character’s traits, then designs the felt material, generates the three views, and checks consistency across angles, clothing, accessories, and distinctive structures. Visible discrepancies are corrected as needed. Details on the back that are not shown in the reference image are completed conservatively and clearly noted. Ideal for original IP characters, picture books and comics, short-form video development, and creators who want to turn a favorite character into a felt-style design. The generated reference sheet can support future image generation, storyboarding, and visual communication within a team. Leave the repeated work of refining material terms, viewpoint terms, and character constraints to this workflow, so you can focus on your character and story.
Glass Refraction Split Poster
Ideal for content creators looking to produce visual posters for people, still life, or products. Enter a theme to generate images from text, or upload a photo you have the rights to use, and specify a two-line title and color scheme. The skill first identifies the subject and scene, then plans a 3:4 vertical split layout: natural photography on top, and displaced transparent glass prisms, partial refraction, iridescent fine-edge highlights, and large magazine typography on the bottom. It calls available image tools to generate the output, then checks the text, subject, and visual layers. Delivery: An actually generated split poster, title, and verification notes; copyable prompts included when needed. Usage: Enter the subject and scene or upload a photo, provide a title, run the skill to check character/product details and text, and adjust as needed. Display images are AI examples generated locally using the skill's visual method and image tools, not real person photos or client cases. Not yet verified on YouMind; results depend on the platform's models and tools. GPT is recommended for text planning, and available generation/editing models are used for images. Limitations: Photo editing requires the current environment to support reference image input, and exact consistency of character identity, clothing, product structure, or cross-frame details is not guaranteed. Accurate text and refraction are not guaranteed every time and require manual review. Without image tools, only pending execution plans can be provided, not final images. Do not upload photos without usage rights or request copying author signatures or brands. Square avatars are cropped by local AI examples with titles overlaid, not new independent cases.
Information
- Version
- v4
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto