I have been tinkering with #AnimateDiff trying to get away from 32-frame movie to unlimited movie length using just home computer GPU.

It's doable. But getting transitions smooth between different shots is tough. But at least it's possible to retain the overall "concept" during the whole movie.

Below example is with stock #StableDiffusion 1.5 & motion module (no LoRA, no fine-tune) with just a static text prompt.

#AI #Noise #HomeComputing #Movies #Animation #Hobbyist

https://aakoskin.kapsi.fi/river.gif

They say the eyes are doors to another dimension.

#AnimateDiff #ComfyUI

Генерация видео: Обзор интересных подходов | Text-2-video | Part 1

План следующий: Методы адаптации T2I в T2V : AnimateDiff, Text2Video Zero Обзор классических подходов : Stable Video Diffusion, CogVideo Новые модельки 2025 : Wan2.1, HunyuanVideo, FramePack Это первая часть из списка статей, тут будет только про T2I в T2V

https://habr.com/ru/articles/910326/

#computer_vision #нейросети #ml #video_generation #собеседования #собеседования_задачи #ai #stable_diffusion #comfyui #animatediff

#aiart #digitalart #stablediffusion #comfyui #skate #skateboard #animatediff #aigenerated

finally progress!

finally!!!

not perfect, not upscaled, not detailed, but good enough for now.

#anime #erotica #animatediff #StableDiffusion #aigenerated