AI Video animation Exploration
Yes it is still the wild-west right now in this space so there is currently no best practice. It’s basically share what’s working best for you at the moment and for me it’s going old school. With making a collage of what I want to be animated. Most people including myself have been generating imagery from textual or image to image prompting and iterating in ComfyUI with Flux, Stable Diffusion and various LoRa’s (a smaller file that contains more detailed info of a subject) touching it all up in Photoshop than moving to 3rd party platform for animation such as Runway or KlingAI. Yup skipping all that and going into Photoshop and cutting up a variety of images and collaging them together not to different than in the 90’s. Granted Adobes generative fill capabilities work wonders. For instance look at the original image of the King he is behind a plate of chicken nuggets on a table. It would have taken several hours to remove all that and add the bottom of his hands. This process was less than 5 minutes by my guess. It was so quick that I did not realize how amazing that was in and of itself. Until I was creating the final PNG to use to generate the video.

Leave a Reply
Want to join the discussion?Feel free to contribute!