Not sure whether this belongs here or in the AI section, but while reading up on prompt-led video generation I came across Muse Video (https://muse-video.app/).
The idea: instead of tweaking a pile of separate controls, you describe everything in one prompt - what happens in the scene, how the camera moves, which details should stay visible, and what audio belongs to the motion - and then compare the result against your original description.
Worth noting that the site itself describes the model as preview-stage: audio-video synchronisation and physically accurate fast motion are still listed as open problems there. So it is more a look at where things currently stand than a finished tool.
Has anyone here played with prompt-based video tools? I am curious how you combine camera and audio directions in a single prompt.
The idea: instead of tweaking a pile of separate controls, you describe everything in one prompt - what happens in the scene, how the camera moves, which details should stay visible, and what audio belongs to the motion - and then compare the result against your original description.
Worth noting that the site itself describes the model as preview-stage: audio-video synchronisation and physically accurate fast motion are still listed as open problems there. So it is more a look at where things currently stand than a finished tool.
Has anyone here played with prompt-based video tools? I am curious how you combine camera and audio directions in a single prompt.
