Sign In

MyMIX-G/Jem

716
5.3k
203
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
903
Reviews
Published
Aug 28, 2024
Base Model
Pony
Hash
AutoV2
92B471C522
default creator card background decoration
Jemnite's Avatar
Jemnite

Don't upload this to PixAI BTW. I will get around to doing it with the correct inference settings and the correct sampler recommendation and the correct negative recommendation. Nobody needs to run 50 steps for this model, that's absolutely stupid.

Edit: After finding two versions of XLS-QromEW imported within 54 seconds of each other, I've come to the conclusion that PixAI is just actually stupid, its users are idiots, and there's no actual point bothering with that site.

Description

Experimental lora-tuning mix. May not be to your taste. Please don't use commercially but feel free to remix. Negative embeddings not necessary for quality but might be helpful.

Heavily modified Gyozamix recipe. Here's a quick rundown of the differences between each model:

  • MIX-GEM-T1: This one is targeting a kind of oil canvas-like texture. It's a very primitive LoRA tuning, just mixing two artstyle trained LoRAs together at a dominant-recessive ratio. The framework it's built on is mostly ad-hoc, as it's the result of some random mixing with surprisingly good results. Decently responsive to prompts.

  • MIX-GEM-T2: (Also called EternalWinter). This one is built on the earlier oil canvas fine-tuning, but with additional work put in to affect a very delicate sort of look. There hints of the mangaka of Galko, Suzuki Ken'ya's style in there. As a result it has very delicate features around the eyes and especially the lashes.

  • MIX-GEM-T2A: (Un-uploaded) A further refinement of T2. Overall it comes with more details and likes to do even more contrast.

  • MIX-GEM-T3: Due to some quirks in the merging process and a failure to account for adjustment in merging materials, this one is stylized with a heavy cartoon influence. It loses some of the delicateness from T2 but also gains more exaggerated features. It's an interesting line to study down towards, though it's not really my preference, so I did not continue down this avenue of investigation.

  • MIX-GEM-T2_2: A more comprehensive rework of T2. Essentially a MIX-GEM-T3 recipe with the imbalance that led to heavy cartoon styling in T3 rectified. It is further enhanced with a CLIP-swap for more prompt-obedience.

I like to use loras from here to modify the output. Character, outfit, and pose loras are fine. As this model is stylized already I don't really see the point in using a style lora. It's not intended to be versatile, use Based66, AuroraOne or Amedira for that.

No HuggingFace repository for this one, recipe (if I bother to provide it) is in the sidebar.

SDXL Update 4/15/2024

We're back with SDXL, lol. Sorry to @penterested, i lied, lol. Using Pony for now since my favorite artists haven't been trained on AnimageXL yet:

  • MIX-GEM-WXL-D2nai: Uses Pony Diffusion for Anime as a base. Worldly_XL is based in at a base level to compensate for Pony's deficiency in backgrounds. It's pretty compatible with LoRAs. I was considering releasing it as a T(aste) version, but novelai is probably the only sdxl model that can survive on the inherent styles within the model and you should just use LoRA to compensate for local.

    • MIX-GEM-WXL-D2naiK: A variant of D2nai with a style lora already baked in. Still compatible with other style loras.

  • MIX-GEM-WXL-ZA1: Also known as ChromeshineXL. This follows in the wake of D2naiK of imparting an inherent style. The primary advantage compared to D2nai is that it has upgraded lighting and better concept recognition for robot girls and monster girls (particularly centaurs). It moves further away from D2nai's realistic bias, the amount of prompt keywords required to remove realism is further reducing.

  • MIX-GEM-LXS-QromEW: This version moves away from the PD for Anime base. I'm not sure yet if it's a one-off case or if it will be the case going forward. It's basically built to serve one single style and it does it fairly decently. It uses ChromelightXL, which is extracted from MIX-GEM-WXL-ZA1, but is otherwise not connected to the rest of the MIX-GEM-XL heritage. Probably a dead end evolution tree here but I get the impression that LS Eqos is a fairly powerful and versatile base so there might be some parallel evolution. This model should be completely unresponsive to style loras.

  • MIX-GEM-LXS-ZA1: (Un-uploaded) An attempt at transposing ChromeShineXL's unique qualia onto LS Equos. Didn't really work out all that well. LS Equos + ChromeLightXL seemed to have better results. Compared to ChromeShineXL there were less watermarks, the backgrounds were better, and the posing seemed to be more dynamic but it lost understanding a lot of a lot of character2character interactions and took major downgrades in lighting and tones.

    • MIX-GEM-XLS-ZA1.trainD: Ended up training the initial differences from D2nai onto LS Equos and merging to finish the final touches. This is ChromeshineXL_MP. The actual model page has more detail on the comparison but basically it's way easier to use and less finicky with LoRAs at the cost of some composition sense.

  • Adam8wit-QEgooW: The sidebar is way more comprehensive than I intend to be in this tab, but essentially it's a heavily redone merge to try to get some use out of the PonyXL T2_2 LyCORIS. It is extremely clean, is great at skintones and lighting, and has fairly decent backgrounds (for Pony, anyways) but has a tendency to stray towards the 2.5D side of things. My recommendation is to use it with character LoRAs when possible to mitigate excessive 2.5D-ness. Unless you like that sort of thing, of course. In that case, go wild. Combine with ChromelightXL to get the milf-faces back again.