Recently, Hedra Labs has released a research preview of Character-1, a technology that allows users to generate dynamic videos of individuals speaking and singing based on any character photo and voice content.
Imagine uploading a character photo and any voice content, and instantly creating a dynamic video that brings the character to life, speaking or singing, with lip movements, expressions, and gestures perfectly synchronized with the voice content! Isn't that exciting?
Official Demonstration Video by Hedra Labs
Key Features and Highlights:
Multi-platform Compatibility: Character-1 can be easily used on both desktop and mobile devices.
Unlimited Duration Generation: The open preview version supports the generation of 30-second videos, and with sufficient H100 supply, 90 seconds of content can be generated every 60 seconds.
Support for Multiple Expressions: Character-1 not only supports dialogue but also handles singing and rapping.
Hedra provides a user-friendly interface that even non-professionals can quickly get the hang of. Users can visit Hedra's official website, use the text-to-speech feature or directly upload an audio file, input character descriptions, and then generate dynamic videos.
Hedra's AI technology ensures high-quality and realistic video content, with satisfying results for character expressions, gestures, and voice synchronization.
From the cases provided by the official website, Character-1 can perfectly perform singing, acting, and expressing different emotions. The technology is not limited to human characters; it can even generate expressive inanimate objects as long as they have distinct facial features.
Using it is also very simple. The specific steps are as follows:
Open the Hedra experience address: https://top.aibase.com/tool/hedra
After entering the page, you can see the operation interface
The interface is simple. Input your character's lines in the first box and choose a voice. Of course, if you don't want to use the generated audio, you can also import your own audio.
Here, I simply input a line: "Hello, this is a speaking video created by AIbase. Today, let's experience Hedra and make video generation as easy as breathing."
Then, in the second box, upload the photo of the character you want to speak. Here, I upload a beautiful portrait I made before.
If you don't have a ready-made picture, you can also input your character in the text box below and click to create.
After the photo is uploaded, click to generate the video in the third box.
Here is the generated video effect:
As you can see, the speaking video generated by Hedra is quite lively. The character not only moves their mouth but also moves other parts of their body and has expressions. However, due to the limited voice options available on the platform, the foreign accent doesn't quite match my photo character. Another drawback is that the generated video is much blurrier than my original photo. I hope the platform can improve the image quality in the future.
Here, I uploaded an audio clip myself. I used Jianying to generate the audio, choosing a female voice, directly inputting the text, and then reading it.
Let's test it again:
Select import audio
The generated effect is as follows:
Then, the blur issue can be resolved using the video enhancement feature of krea ai, but be aware that for free trials, the video duration cannot exceed 10 seconds. For longer videos, you'll need to trim them. Also, don't choose too high a frame rate; I chose 60 frames per second and had to pay for an upgrade halfway through, which was quite disappointing.