Poor Sadzilla.

Aw, shucks! Thank you, I’ll get a new challenge up shortly.

I like that he’s holding up his horse skin, as if he needs a pair of suspenders to keep his disparate parts together.

Been lurking for a long while, thought I’d finally jump in on the fun. This uses a Flux derivative model called STOIQO Unleashed for an initial pass, then I upscale the latent and run a second pass using the new Flux Krae model.

I was having the same issue with my community and personal icons/banners. What fixed it for me was to resave the image with a different compression level. I did quality 11 instead of 12 in Photoshop. After that it uploaded without the error.

Theres a bunch of non-consensual face-swap and nudifier garbage here. That shit needs to be banned so fast, it’s really gross.

Look like lemmynsfw has been having hosting issues and are trying to migrate the photo archive. Hopefully that gets resolved soon.

See for details: https://lemmynsfw.com/post/28224732

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.

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.

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.

♥️

Thank you, I’m glad you like them.

Sometimes the AI just really wants to make nipples.

I agree about the color. I keep refining and iterating as I go, so the images towards the end of a series always seem to be better than the earlier ones.

I really appreciate you noticing. I spent a ton of time and lots of trial and error on fine tuning settings to get that volcano effect.