Facial expressions must be crafted as drawings to be readable on small screens
Facial expressions must be crafted as drawings to be readable on small screens
在小屏幕上，面部表情必须通过绘图来呈现才清晰可见
📝 Originally published (in Japanese) at forge.workstyle.tech. In a vertical video where two caricatures converse, the supporting character’s expression changes to a troubled look midway through. Initially, I specified the facial expression using a prompt similar to what you’d use for creating lip-sync videos: “eyebrows drawn together and slanted down, mildly troubled expression.” 📝 本文最初以日语发布于 forge.workstyle.tech。在一个两个卡通人物对话的竖屏视频中，配角的表情在中途变为困扰的神情。起初，我使用了类似于制作口型同步视频的提示词来指定表情：“眉毛紧锁并向下倾斜，略显困扰的表情”。
During the screening review, I received this feedback: “Sam’s confused eyebrows remain difficult to read at this display size.” The supporting character is about half the size of the main character and is placed deeper in the scene. On a 1080×1920 screen, the face is only a few dozen pixels. The expression added via the prompt got lost in the lip-sync movements, making it nearly indistinguishable from the original face. 在审核过程中，我收到了这样的反馈：“在这个显示尺寸下，Sam 困惑的眉毛依然难以辨认。”配角的大小约为主角的一半，且位于场景的更深处。在 1080×1920 的屏幕上，脸部仅占几十个像素。通过提示词添加的表情在口型同步的动作中被淹没了，导致它与原始面部几乎无法区分。
Creating as an Image
以图像形式创作
The single image that serves as the basis for the lip-sync video was replaced with a worried-looking face. This is derived from the original caricature using img2img. Original image → img2img (denoise 0.5) “Furrow your brow, look slightly anxious, close your mouth, and keep the clothes and pose the same.” 作为口型同步视频基础的单张图像被替换为一张带有忧虑神情的脸。这是通过 img2img 从原始卡通形象衍生出来的。 原始图像 → img2img (去噪强度 0.5) “皱起眉头，看起来略显焦虑，闭上嘴，保持衣服和姿势不变。”
When compared, the difference was clear. The eyebrows are lowered, and the corners of the mouth droop. By recreating the lip-sync video based on this image, even on a small display, it was apparent that the character was “struggling.” The review treated this suggestion as resolved. 对比之下，差异显而易见。眉毛降低了，嘴角下垂。通过基于这张图像重新制作口型同步视频，即使在小屏幕上，也能明显看出角色正在“挣扎”。审核认为该建议已得到解决。
Redrawing from scratch makes it a different person
从零开始重绘会导致角色变样
I have also generated a picture with a different expression from scratch. I added a “worried face” to the same description of appearance and had it drawn. It became a different person. The hairstyle and contours are slightly different. The viewer perceives it not as the same person with a changed expression, but as a different person appearing. 我也曾尝试从零开始生成一张带有不同表情的图片。我在相同的容貌描述中加入了“忧虑的脸”并让 AI 绘制。结果变成了另一个人。发型和轮廓略有不同。观众感知到的不是同一个人的表情变化，而是出现了另一个不同的人。
With img2img, the lines, colors, and clothes are inherited from the original picture. Only the expression changes. Denoise is around 0.5—0.62. The higher it is, the more the expression changes, but it approaches becoming a different person. 使用 img2img 时，线条、颜色和服装都继承自原始图片，只有表情会改变。去噪强度在 0.5 到 0.62 之间。数值越高，表情变化越明显，但也越容易变成另一个人。
Some Expressions Cannot be Erased
有些表情无法被抹除
The reverse approach did not work well. The main character’s portrait initially had a smiling face with an upturned mouth. I wanted to give it a calm expression, so I tried to erase the smile using img2img: “completely neutral face, straight closed mouth with level corners, absolutely no smile.” 反向尝试的效果并不理想。主角的肖像最初是一张嘴角上扬的笑脸。我想给它一个平静的表情，于是尝试用 img2img 抹除笑容：“完全中性的脸，闭合的直线嘴，嘴角水平，绝对没有笑容。”
Even with denoise 0.5 or 0.6, the upturned mouth remained. The teeth became invisible, but the faint smile would not disappear. The nature of the original image made it difficult to alter using img2img. It would have been faster to create a character with a neutral expression from the initial image. 即使去噪强度达到 0.5 或 0.6，上扬的嘴角依然存在。牙齿虽然看不见了，但那抹淡淡的微笑却无法消失。原始图像的本质使得它很难通过 img2img 进行修改。如果从一开始就创建一个表情中性的角色，效率会更高。
1. Expressions Created Once Can Be Reused
1. 一旦创建，表情即可复用
The opposing character, Sam, appears in dozens of episodes. By creating a single image of a worried face, the same worried face can be used in any episode. Expressions can be switched by simply writing “this face from this line” in the script. 对手角色 Sam 出现在几十个剧集中。通过创建一张忧虑表情的单图，同样的忧虑表情可以在任何剧集中使用。只需在脚本中写上“从这行台词开始使用这个表情”，即可切换表情。
To switch expressions in scenes without lines (e.g., when Sam looks worried the moment he hears “let’s try”), a specification to switch expressions without lines was added.
{"t": "expr", "at": 4.32, "speaker": "sam", "expression": "worry"}
为了在没有台词的场景中切换表情（例如，当 Sam 听到“我们试试吧”时表现出担忧），我们添加了无需台词即可切换表情的规范。
Expressions are retained until the next change. If the face returns to normal after each line, it becomes unclear what Sam was worried about. 表情会一直保留直到下一次更改。如果每行台词后脸部都恢复正常，观众就无法理解 Sam 到底在担心什么。
Summary
总结
- The expressions of small characters in an image are not conveyed through prompts, so create them as illustrations.
- 图像中小型角色的表情无法通过提示词传达，因此请将它们作为插图进行创作。
- Expression variations can be derived from the original image using img2img; drawing from scratch will result in a different person.
- 表情变化可以通过 img2img 从原始图像衍生；从零开始绘制会导致角色变样。
- The inherent nature of the original image (e.g. a smiling mouth) is difficult to erase using img2img; decide on it in the initial illustration.
- 原始图像的固有特征（如微笑的嘴）很难通过 img2img 抹除；请在初始插图中就确定好。
- Once a facial expression illustration is created, it can be reused throughout the entire story where the same character appears.
- 一旦创建了面部表情插图，它就可以在同一角色出现的整个故事中重复使用。