Not even sure how this is going to look in a post, the video is kind of large. Been playing with some of the new image-to-video generators, and stitched 7 segments together into a one minute video:

https://files.catbox.moe/j86bvw.mp4

This is from one of my favorite early Flux posts, Paintshop in Orange.

  • CavendishOPMEnglish
    2•3 days ago

    Would love to do this locally, but my machine would probably choke. This is from an online provider, KlingAI. When I experimented with Stable Diffusion AnimateDiff models, it took nearly 20 minutes for a low res, pretty cruddy looking 4 seconds, and 90% were straight up garbage.

    I’ve only used the fp16 Flux models, it’ll do a 2 megapixel image in 2ish minutes. I haven’t tried the compressed models, or the GGUF models geared towards lower VRAM cards.