Introduction to Beholder Vision
Beholder Vision began as an experimental LyCORIS-LoCon for Illustrious-XL v0.1, trained on 126 meticulously curated images of aesthetic anime art.
The concept: create “eye-candy” results, with flexibility to adapt to a variety of creative needs.
Usage Recommendations
Illustrious Ver. Parameters (Recommended as of Nov 30, 2024):
Strength: 1.0–1.2 (personally go for just 1.0)
Sampler: DPM++ 2M SDE (Karras)
Steps: 25–35
CFG Scale: 6–7
Changelog and Updates
Dec 6, 2024
Version 3o is here!
Full support for v-prediction models such as NoobAI-XL V-Pred-0.65S-Version, which this version is based on.
Dec 4, 2024
Version 2.1o is now available! This marks a complete rework of the initial test version for Pony. It has been trained for 5,490 steps, making it competitive with the original Beholder Vision.
Despite its extensive improvements, the new LoRA is just 54.8MB—half the size of previous Pony iterations of the model and vastly enhanced in every aspect.
Dec 2, 2024
The first version of Beholder Vision for FLUX.1 [dev], 1.3o, is now out.
Nov 30, 2024
I’m excited to announce Beholder Vision 1o (and its successor, 1.1o)!
1o debuts as an experimental GLoRA, while 1.1o returns to classic LoCon, delivering improved performance at a smaller file size.
Now natively compatible with other SDXL models, including NoobAI-XL Epsilon-pred 1.0-Version.
This version represents a significant leap forward over the 0.9beta, thanks to an upgraded training dataset and finely tuned parameters. (Details on the dataset and parameters will be shared if there’s interest.)
Description
Pruned four images out of the dataset (for a total of 122), trained as a GLoRA which increased the size of the file by a substantial amount. Next version, I plan to train as a LoCon again.