TL;DR
V2 is the main Pony version, including the "classics" LoRA (InCase/Vixon/Expressiveh/Disney)
Juice is variant of V2, more shiny, more crazy
IXL is the first Illustrious version, in the style of V2
IXL V0
First release of an Illustrious XL version of BancinXL, based on AnBan_Illus. I did not want to release a V3 of AnBan and felt like it was close enough to be released as a V0 here. Need some more work but getting close! (the model is a bit moody for now regarding fidelity to prompt) :D
Check AnBan for tips on usage (since it is different from a Pony model :D), basic idea is to just remove the Pony Scores and add the Illustrious quality tags. I still use also some Pony Negative embeddings, check the showcase pictures :D (PS: it's an Epsilon Prediction model!)
It was built by adding a smidge of Initium (between 0.05 and 0.1, i don't remember the exact amount) to jolt the text encoder and then i merged on top of it:
Bancin LoRA for AnBan (at 1.05)
ExpressiveH (at 0.3, i know it's a Pony LoRA, but i felt like it was kinda doing something)
Darker than dark (at 0.1, to curb a bit the overbearing glow)
Juice!
PsychoNex is like a hard liquor, tasty but drink it pure and you'll go blind ;-)
I have told in many posts that i love these models, but sometimes, working with them is not yielding what i wanted (but maybe, what i deserved :D).
The Juice version of BancinXL is simply a 50/50 merge mix of PsychoNex and V2.
Not intended to be the main version, but still a whole lot of fun for more chaos :D
Go check Skumerz work!
V2
Rework of the V1, with a similar approach, with just a few more LoRA to give it some oomph.
Still based on Pony XL v6, before jumping on the Illustrious/NAI XL trend :D
Recipe:
BancinBase (using SuperMerger):
All Disney Princesses V1 (1.0) [Tried the Pony version, V1 still the better fit]
ExpressiveH (0.65) ❤
InCase Style [PonyXL] V3 (0.55) ↑ 0.05
Vixon's Pony Styles Gothic Neon V2 (0.35) ↓ 0.1
Cutesexyrobutts Style PDXL V3 (0.25) 🆕 [After dimension rework from 16 to 32]
Style for PonyXL V6 - Smooth 2 (0.15) 🆕
Detail Tweaker XL - V1 (1.2) 🆕 [After dimension rework from 16 to 32]
BancinTemp (using Checkpoint Merger):
0.8 x BancinBase + 0.2 x BancinXL V1
Baked in VAE: FlatPieceXL (switch from SharpSpectrum, still good colors, just less strong)
BancinXL_V2 (using SuperMerger):
BancinTemp + (0.4) x Detailed/Perfect Hands
Usage:
I have added a step/sampler comparison to help choose, but the model works good with the classics without any issues. Euler a give more smooth picture while DPM++ 2M give more crisp results.
For Euler a, 40 steps give a better looking result, while only 20 steps are enough for DPM++ 2M.
DPM++ 2M SDE change the composition a bit but is nice for experiments.
I tend to use CFG between 4 and 6 to give more or less liberty to the generation, but that's a personal preference.
Regarding prompts, most are done with the classic Pony scores stuff, here is what i do for reference:
Expressiveh, (optional LoRA trigger words), masterpiece, best quality, PonyScores7, <1girl|1boy|1other>, (character name as recognized by Pony), (body description), (scene description), (background and lighting)For negative prompt, except for specific, it's always this:
PonyScoresNeg, (worst quality, low quality:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, bad hands, missing fingers, extra fingers, fused characters, muscular female, deep_negative_ponyEmbeddings used (real SDXL TI, SD1.5 TI are useless unless you hack stuff in ComfyUI, yes, i am looking at you EasyNegative ^^;):
Personal trick:
I personally prefer the crispiness of DPM++ 2M for the overall picture, but faces are generally better with Euler a.
To mix the best of both, I generate using DPM++ 2M with 40 steps and when ADetailer kicks in, it is configured to switch only the sampler for the face to Euler a (will keeping steps, prompts, clip skip and so on).
Simple and does the trick, didn't want to bother with also choosing CFG/Steps/etc...in the extension. :D
V1
So. A very simple merge to integrate the LoRAs the amazing creator Bancin use in almost all his/her pictures ^^; (GO CHECK HIS/HER WORKS!)
Made to allow trying his "style" on my GPU poor setup without overloading it too much.
Base model: Pony XL v6
LoRAs and weights:
All Disney Princesses V1 (1.0)
ExpressiveH (0.65)
InCase Style [PonyXL] V3 (0.5)
Update: Wow, scrolled the Disney Princesses Gallery and discovered everyone and more are using approximately the same mix of lora ha ha ha. Lots of VRAM consumed on merging those with Pony each time instead of using a pre-baked one ^^;