👩🎤Model V6 - Portrait Video Guide
The difference between V6 and- Portrait Avatar and V1 Audio Lipsync is that Audio Lipsync, requires a video and an audio, while portrait avatar will change a photo to become a video, while syncing
Step 1: Get started
Login to your Ask Akido Tools Dashboard https://akidotools.ai/dashboard.
Click on Model V6
Step 2: Upload an image you want to bring to life (Max 15MB)
Step 3: Upload an audio you want to add to the image, (The shorter your audio, the faster it loads)
We recommend using an audio that less than 30 seconds.
Step 4: Choose the configuration you want.
Omnihuman setting creates hyper-realistic talking/singing videos from one image and audio, delivering lifelike results with AI lip sync in minutes, this costs 30 credits
Here fast generation often comes at the cost of quality, while slower generation can lead to higher-quality result
When you choose to use the Slow quality, you can set its computing intensity, the higher the intensity the longer it takes to generate
The higher the intensity also moves the surrounding environment even more.
We recommend using Omnihuman to test out .
Step 5: Once you are ready, click on “Submit”
Step 6: View your picture.
On your dashboard, click on the Task List.
In the task list, choose Model V6 - Portrait Avatar in the drop down, and play/ download your video
Last updated