blaze466 I'll consider your proposal; however, I'm at a very early stage of learning both image and video generation, so the work is trial and error. Therefore, I would hope that a VR expert, someone who knows what they're doing, will appear (I ask Gemini what to do 😃). Also, we have to consider that there are costs associated with each image or video generation.
The process requires the following:
In venice.ai, I need to provide a suitable prompt to generate the image that will later be converted into a video: For example, "10 girls doing X, at X distance, photographed with lens X..."
Then, in the same venice.ai, generate the prompt for the video: "The girls approach, look at you, laugh..."
Provide the appropriate parameters to owl3D, which aren't many.
Steps 1 and 2 are done on the web, and for step 3, I'm using a Mac Mini M4, and the 10-second generation takes an hour.
If the prompt for step 1 wasn't very good, I'll only see the result at the end.
What I'm getting at is, if I started doing this a week ago without really knowing what I was doing, I'm amazed at what we'll be able to do in the future.
Sorry if something isn't clear; I don't speak English and I'm using a translator.
