Version names includes the base model it was trained from, use appropriate version for each model. Rouwei version wont work well with noob, the opposite is also true. Old noob versions would be too weak on a fresh noob checkpoints also, eps and vpred should also be used with their dedicated versions. Don't forget to check version descriptions for more specific info and list of supported style tags.
Anima v4 info: Update for recent anima preview 3 version. List of styles is same.
Anima v3.5 info: Same version as anima-p2_v3, but trained of full range of blocks. Should™ just work better overall. Out of dataset test still fine. List of styles the same, grid
Anima v3 info: V3 is version trained from and for anima preview 0.2. Still won't affect data outside of dataset so much. Style list is same with v2, grid with styles.
Anima v2 info: A bit late, since 0.2 preview is already out, but whatever. It was trained from 0.1 version of preview model. Catastrophic forgetting was addressed and improved, at least it's not so disastrous now. Mixing between styles was also a little bit improved from empirical tests. List of all styles and grid. It would not work as well with 0.2 preview.
Anima v1 info: Anima version of lora comes with limited dataset. List of styles that comes with it. More like a test version. Model is in early stage and too incoherent at something above 1mp. If you decide to upscale, you would need to use tiled methods, unless you're okay with artifacts. Style tags should be invoked with @ before them. Mixing somewhat works, but not how it was with default xl weighting, rather like compel mode.
MIO - mix in one versions with mix of ai styles and some real artists in dataset.
BIO - best in one versions, containing only artificial images in dataset. 90% filled with naiv3 or styles from local models with very distinctive look only.
Description
Version trained from Noob-vpred-1.0 checkpoint. One of the cleanest from artifacts version due to edm2, simple example of that. Should work fine with cfg++ and classic samplers. Some of previous version styles was dropped for various reasons. List of all styles in this version. Hello Asuka example grid of all styles.
FAQ
Comments (7)
if you could tell me what params you used for edm2 i would appreciate it
Edm2 related settings was https://files.catbox.moe/djiy2u.txt but actual decaying started at about a third of the way due to how distributed training works, so probably would need to set 0.3 instead of 0.9 there
165mb png, you animal.
But with cute ears tho
I have been genning a lot with this lora, it's a true powerhouse to just fix up NAI 1.0 v-pred models. I personally like 4.02 the most for my usecase after recent testing with the newer version. 4.02 works extremely well to apply mixes of styles from the lora with innate artist tags, imo gives the best detail in base gens and when upscaling with multidiffusion. v5 and v6 are a little better by themselves when used as the sole style influence.
My personal favorites are deadpurity, lucifel99_type2 and firedotinc.
But even without adding a style tag from the lora just adding the lora and using innate artist tags fixes the models up in a very pleasant way.
Goated Lora!
I actually liked how v4 turned out too and will probably fork from that dataset in the future
@bakariso Hell yea, you did it! Praise be onto you.