在线调试
填写业务相关参数免费在线调试
该分类下无相关接口
当前生成一个的时间很长,比较占用排队资源,仅限尝鲜使用
返回格式:application/json
请求方式:HTTPPOST
请求示例:
Creating with Act-One on Gen-3 Alpha
在 Gen-3 Alpha 上使用 Act-One 进行创作
Introduction 简介
Gen-3 Alpha is the first of upcoming models that offer improvements in fidelity, consistency, motion, and speed over previous generations of models.
Gen-3 Alpha 是即将推出的一系列模型中的第一个,这些模型在准确度、一致性、运动和速度方面相对于上一代模型有所改进。
Act-One allows you to bring a character image to life by uploading a driving performance to precisely influence expressions, mouth movements, and more.
Act-One 允许您通过上传驾驶表演来使角色图像栩栩如生,精确地影响表情、口型动作等。
In this article, driving performance refers to the video that will influence an image. Character image refers to the image that will be animated by the driving performance.
在这篇文章中,驾驶性能指的是会影响图像的视频。角色图像指的是会被驾驶性能动画化的图像。
This article outlines how to use Act-One on Gen-3 Alpha, input best practices, the available settings, and more.
这篇文章概述了如何在 Gen-3 Alpha 上使用 Act-One,输入最佳实践,可用设置以及更多内容。
Spec Information 规格信息
Spec 规格 Gen-3 Alpha 三代阿尔法
Cost 成本 10 credits per second, 50 credit minimum
每秒 10 积分,最低 50 积分
Maximum output duration 最大输出持续时间 30 seconds 30 秒
Explore Mode on Unlimited Plans
无限制计划的探索模式 Yes 是
Platform availability 平台可用性 Web 网络
Required base prompt inputs
所需的基本提示输入 Video 视频
Image 图片
Output resolutions 输出分辨率 1280x768
Frame Rate (FPS) 帧率(FPS) 24fps 24 帧/秒
Best Practices for Act-One Input
一、最佳实践:输入第一幕
Before diving in, review these best practices to ensure that your input selections will set your generation up for success. Most output issues can be addressed by using inputs that follow these recommendations.
在深入研究之前,请回顾这些最佳实践,以确保您的输入选择将为您的生成工作奠定成功的基础。大多数输出问题都可以通过使用遵循这些建议的输入来解决。
Driving Performance 驾驶性能
Well-lit with defined facial features
光线充足,面部特征明显
Single face framed from around the shoulders and up
单个脸框从肩膀周围向上
Forward-facing in the direction of the camera
面向摄像头的方向
Face is in frame for the entire video
整个视频中面部都在画面内
Ensure the face doesn't move in and out of the frame
确保面部不要在画面内进进出出
Clear mouth movement and expressions
清晰的口部动作和表情
Certain expressions, such as sticking out a tongue, are not supported
某些表达,例如伸出舌头,不被支持
Minimal body movement 最小的身体活动
No face occlusions in frame
画面中无面部遮挡
No cuts that interrupt the shot
不允许打断镜头的剪辑
Follows our Trust & Safety standards
遵循我们的信任与安全标准
Character Images 字符图像
Well-lit with defined facial features
光线充足,面部特征明显
A single face framed from around the shoulders and up
一张从肩膀以上框出的脸
Forward-facing in the direction of the camera
面向摄像头的方向
Follows our Trust & Safety standards
遵循我们的信任与安全标准
Step 1 – Uploading the Driving Performance
第一步 - 上载驾驶性能
Begin by navigating to Generative Video in your Dashboard.
从您的仪表板开始,导航至生成视频。
From here, make sure the Gen-3 Alpha model is selected from the top left corner dropdown. You’ll find the Act-One icon in the left hand toolbar:
从这里,请确保从左上角下拉菜单中选择 Gen-3 Alpha 模型。您会在左侧工具栏中找到 Act-One 图标:
In the top half of the Act-One window, drag and drop a new video or select an existing video from your Assets to add your driving performance.
在一幕一的上半部分窗口,拖放新的视频或从您的资产中选择现有的视频以添加您的驾驶表现。
Make sure that the driving performance follows our recommended best practices for the best results.
确保驾驶性能遵循我们推荐的最佳实践,以获得最佳结果。
Your driving performance should always be forward-facing, even if the character image you plan to upload is in a different angle.
您的驾驶表现始终应面向前方,即使您计划上传的角色图像角度不同。
Preliminary face-detection will run on your driving performance before you’re allowed to generate.
在您被允许生成之前,初步的面部检测将会对您的驾驶表现进行运行。
Below are examples of driving performances and their outputs:
以下是驾驶表现及其输出的示例: 以下是驾驶表现及其输出的示例: 1. 表现:平稳驾驶 输出:车辆行驶平稳,油耗低 2. 表现:高速行驶 输出:车辆加速迅速,稳定性高 3. 表现:城市驾驶 输出:车辆操控灵活,停车方便 4. 表现:越野驾驶 输出:车辆通过性强,适应各种路况 5. 表现:节能驾驶 输出:车辆燃油经济性好,环保 6. 表现:运动驾驶 输出:车辆动力强劲,驾驶乐趣高
Driving performance 驾驶性能 Output 输出
Once your driving performance is uploaded, you’re ready to choose your character image.
一旦您的驾驶表现上传完毕,就可以选择您的角色形象了。
Step 2 – Selecting the Character Image
步骤 2 – 选择字符图像
Select the character reference image in the bottom half of the Act-One window.
在一幕一窗口的下半部分选择角色引用图像。
Choose from an existing preset image, or switch to the Custom tab to upload your own.
从现有的预设图片中选择,或切换到自定义选项卡上传您自己的图片。
Act-One can support a wide variety of input images, but images that closely follow our best practices will provide more consistent results when compared to more experimental images.
Act-One 可以支持各种各样的输入图像,但遵循我们最佳实践的图像与更具实验性的图像相比,提供的结果会更加一致。
Below is a chart that outlines our recommendations in more detail. Variations annotated with a ✅ should work well in most cases, ⚠️ may sometimes work or provide unexpected results, and ❌ will likely not provide ideal results in most cases.
This chart isn’t meant to deter experimentation, but rather act as a resource for those who need each generation to be satisfactory. Don’t be afraid to travel outside of these recommendations if you’re looking to push the limits of Act-One.
Category 类别 Variation 变化 Example 示例 Support 支持
Character type 字符类型 Human 人类 ✅
Non-human ❌
Character angle Forward-facing/Front view ✅
Profile view ❌
Character distance Shoulders and up ✅
Torso and up ✅
Full body ⚠️
Character silhouette Intermediate ✅
Complex ⚠️
Step 3 – Generating the Act-One Video
步骤 3 - 生成第一幕视频
You can hover over the duration modal to see the calculated credit cost before generating.
Click the Generate button after confirming that you’re content with the selected inputs and credit costs.
Your video will begin processing in your current session, where each video will be available for review once complete.
Understanding Act-One Pricing
Act-One charges 10 credits per second with a minimum of 5 seconds. This means that driving performance videos under 5s will result in a charge of 50 credits.
After the 5 second minimum, each additional second is charged 10 credits, with partial seconds accounted for and rounded up to the nearest decimal. In example, a 5.6s driving performance would be charged 56 credits.
Reiterating and Troubleshooting
重申和故障排除
Most issues or errors will be specific to your driving performance or character reference image inputs and can be resolved by ensuring that the inputs follow the recommended best practices.
Below is a list of Act-One errors and how to troubleshoot them:
Error Troubleshooting 故障排除
Unable to detect a human face in your video. Ensure driving performance is properly lit and the face is unobscured and centered in frame.
Unable to detect a human face in your image. Ensure character image follows best practices.
确保字符图像遵循最佳实践。
An error occurred while detecting a human face in your video. Please try again later.
在检测您的视频中的人脸时出现错误。请稍后重试。 Ensure driving performance contains minimal body and background movement.
确保驾驶表现中包含最少的身体和背景移动。
We detected unusable audio from your video.
我们检测到您的视频中有不可用的音频。 Ensure the audio of your driving performance complies with our Trust & Safety standards.
确保您的驾驶表现的音频符合我们的信任与安全标准。
This content was flagged by our moderation policy.
此内容被我们的审核政策标记。 Ensure the character image complies with our Trust & Safety standards.
确保字符图像符合我们的信任与安全标准。
There may be cases where you don’t encounter an error before generation but receive an issue in your output. These edge cases can generally be resolved by following the best practices or re-running a generation:
可能在生成之前不会遇到错误,但在输出中会遇到问题的情况。这些边缘情况通常可以通过遵循最佳实践或重新运行生成来解决。
Issue 问题 Troubleshooting 故障排除
Face improperly detected
面部检测错误 Use a character image that follows best practices.
使用遵循最佳实践的字符图像。
Intermittent artifacts 断续的文物 Re-run the generation.
子程序名 | 返回值类型 | 公开 | 备 注 | ||
__启动窗口_创建完毕 |
子程序名 | 返回值类型 | 公开 | 备 注 | ||
Send_API |
变量名 | 类 型 | 静态 | 数组 | 备 注 | ||
REQU_Data | 文本型 | 提交字符串 | ||||
return | 文本型 | 返回字符串 | ||||
API_URL | 文本型 | 接口地址 | ||||
API_KEY | 文本型 | 接口密钥 |
请 登录 后发表评论
填写业务相关参数免费在线调试
生成符合你的开发语言代码,复制即可
调整你后端部分逻辑代码即可上线使用
客服微信
joieme
请打开手机微信,扫一扫联系我们
返回顶部