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.
I saw on another comment you mention you have a 3090, how long did this take to make? Do any of the compressed Flux models generate any faster for you?
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.
Ahh okay, cheers. Thanks for the reply.