Hello , can you please develop new photo enhancement model dedicated for video frame images ?
I believe this will be really useful for many users ! Many times i just get much better results using Video AI and Proteus model (for example) to upscale video frame image sequences then all the existing Photo AI models can provide . So i think we can get much better results in Photo AI with new specific model especially developed for such purpose !
Video AI is different than Photo AI, the AI has to work temporally (and not just when interlaced) Putting together frames processed by Photo AI is going to give a temporally weird result with each frame landing on a different solution.
Just look at older TVs that had non temporal noise reduction and watch the faces swim.
