LoRa extract of 4th tail model.
2 sizes, XL/L and XL-alt. The bigger - the more accurate.
New version was made with some new approach, it should look better and represent more, but compatibility issues may occur. Please report if you meet any, will try to fix it.
XL-alt looks a bit different in terms of style but works best to get full color and brightness.
Before using - check out merge of full weights. May be you will find it more satisfying.
Original model comes with 8000+ artists styles, lots of anime characters (kemonomimi, gacha, touhous, vtubers, etc.), concepts and some other features.
After LoRa compression some artist are fine, some are damped but still works, others barely recognizable. Same for character knowledge, tags, style mixing. Quality tags seems working.
But who cares if you only want to use a small part that satisfies you directly on your favourite model?
Also consider using higher LoRa weight.
Works with PonyDiffusion finetunes/mixes including Autism.
Prompting:
by ARTISTNAMEby is mandatory, then quality tags, your prompt with full character name like on boorus. Check out 4th tail description for more.
Description
Update
FAQ
Comments (5)
which one in 0.5.0 can use with Comfyui? or none of them?
With comfy you can use any, XL is probably the best choice.
Omg. Just wait for the popularity of this lora to go through the roof in Civitai. 0.7~0.8 weight works like a charm for all my pony base models.
Question, is this only a collection of certain artists? I looked for an artist named nezumi/nezumin & nezunezu, but didn't see anything.
Well, this is a lora/lycoris extract from trained model one of the features of which is style knowledge knowledge. List of known artists can be found in original description, how they work in extract - need to check exact one, it performs worse then full weights.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.