alex swain March 15, 2025 0 Comments

Updated Fall 2025

WAN/Video

I trained my bleach bypass dataset of WAN 5b and 14b (2.2) into a LoRA. Considering how much smaller and faster inference is for 5b I’ve been leaning it a lot more for quick outputs. The difference in quality is not much from my experience in making sub-60s videos. It’s great for Halloween stuff.

This is the 5b example of applying the LoRA. Considering there are only about 6 movies filmed entirely in BB I figured I’d keep the theme of one of them.

Wan 2.2 5b using a bleach bypass LoRA.

FLUX/SDXL

These are some examples of fine tunes or LoRA’s I purpose built.

These are rough storyboard-like images to lay out the neighborhood where the book mostly takes place.
LoRA augmented from photorealistic training set to generate a hybrid sort of photoreal/illustrative output

examples of synthetic images generated to augment “light” datasets. These end up as hybrid illustrative/photoreal panels such as above. These were generated from a LoRA trained on hundreds of original photographs from “down the bayou”.

wonky powerlines be damned!

TBD; Nighttime-trained LoRA examples. Kodachrome, APX100 , Bleach Bypass, etc. Poor low-light trained models etc.