Hello everyone. I am Dr. Furkan Gözükara. PhD Computer Engineer. SECourses is a dedicated YouTube channel for the following topics : Tech, AI, News, Science, Robotics, Singularity, ComfyUI, SwarmUI, ML, Artificial Intelligence, Humanoid Robots, Wan 2.2, FLUX, Krea, Qwen Image, VLMs, Stable Diffusion
Hello all! I'm working on animatoins using AnimateDiff. Is there a way, to use a series of images and have stable diffusion animate the motion between them? for example, it would be images of a man walking, but only like 4, i want to extend those 4 frames to 16 or 32 and have stable diffusion make the frames between so the motion looks smooth. Is that possible? Am I describing it correctly?
That's my problem with openpose, which the developers didn't solve, that it only works when you can see your face. Even though all lines and connection points are different colours, you cannot detect a partial human body with openpose. It only works if there is a face or head in the picture.
That's why my Lora models trained on RV 5.1 work beautifully on it, and I get nicer quality. So I'll continue to train on RV 5.1, but I'll be generating with it from now on. (The datasheet is wrong, this is SD 1.5!)