Starting image:
Here's an updated version with a grain and focus blur pass. Also not looped, which might also contribute some to the uncanny valley effect.
*edit - F it, I'll just replace the original video with the grainy one, it's better.
The Flux workflow has a post-process step at the end that adds film grain, a photographic color grading, and a little bit of focus blur. The videos don't use this post-process step, and I wonder if adding a film grain pass on those frames would help too. Something to look into adding.
Appreciate the feedback!
The original starting frame, from Flux.
Yes, this is all local and self-hosted.
On the hardware front, I'm running an Intel 12900k, Nvidia 3090, 64GB ram. The workflow is all done with ComfyUI. Starting with a single image from the Flux 1 Dev model (text to image). Then passing that to a new video model called WAN 2.1 for the image-to-video.
The Flux image takes about 2 minutes to generate but I make them big, about 2.5 megapixels with an upscale/finetune pass. The video takes about 3-4 hours to output 10 seconds of 720p at 15fps. Any larger res or more frames and I get out of memory errors. After that, I run it through a script I wrote using a frame interpolator called RIFE to get it up to 30fps.
If you don't need NSFW and don't mind a Chinese company doing the video, I've gotten great image-to-video results from KlingAI in just a few minutes. The company behind Flux is also working on a local i2v model, and there's another new one called HunyuanVideo that just came out a few days ago but I haven't tried it.
Here's the full-res starting image I made with Flux some months back.
The image generators seem to have a hard time with continuity when something passes in front, like her arm in front of the bikini straps.
This looks straight out of an 80s B-movie. I dig it.
Definitely. Full nudes are okay, but wacky outfits are fun to experiment with. I like the clear plastic infill panels on this one.
The starting frame from Flux:
And, a bonus outtake where a camera lens got in the frame, for some reason known only to the AI.