This model works correctly only with config file. Place this file in the same folder as this model.
Fluffy Universe (old name Furry DreamShape) is my personal staple mix that I update to suit my needs, and I do LORA training on it as well.
This model merged with such well-known models as YiffyMix, DreamShape, BB95, Koji, epic realism and the core of this model is the best model today in my opinion - FluffyRock
As for samplers, I most often use the most powerful "Restart". I experiment a little less often with various subtypes of DPM++ 3M SDE.
Tag Autocomplete File - courtesy of FluffyRock's tag database.
This model is universal and suitable for generating a variety of objects, including realism.
I express special gratitude to each author of the listed models present in my mix.
LORA training on models with the FluffyRock base includes the following instructions:
Must be activated "parameterization v". This setting is located in the tab when selecting the base model.
The program may display an error that this model does not support this function. Ignore the warningit is advisable to use the parameter "noise_offset" around 0.1-0.9.
Reminder
Model 1.0 is my old mix without FluffyRock. However, this mix is useful when working with common lore.
LoRAs trained on non-vpred FR models may perform significantly worse on newer versions my mix.
Description
FAQ
Comments (7)
Best checkpoint so far! I've used about 100 different ones and none have been as easy to use and forgiving as this one!
Thank you so much! I haven't quite figured out how I got it so well. I'm still trying to mix models, and I can't beat this version yet. But this checkpoint is very similar to EasyFluffyRock, but the colors here work a little bit more correctly than there, and I noticed a little less artifacts on the checks here.
I'm consistently getting slightly worse results with Universe 1.0 than with Dreamshape 2.1. In what ways / for what kinds of output is Universe better suited?
Checked a lot of seeds, especially those related to dynamic actions. Fluffy Universe showed much better results, especially with sitting poses. Do you use negative embeddings in your projects? In most cases, they work disgustingly and greatly degrade the quality of generation, especially the color palette suffers. The only two embeddings I can single out are deformityv6 and bad hands. Everything else is just often a complete trash. But even they should be used carefully. I would also not mind if you showed me the strength and simplicity of generation, where the latest version is significantly inferior to the previous one.
@deygdrixe221 Sometimes I use boring_e621, but that's it. And nothing is significantly inferior. Except maybe backgrounds, those tend to be less sharp and detailed. But there's also just slightly less tendency to respect artist tags (like your first example, tsampikos - fur tufts and ear/tail shapes are less faithful), less detailed hair, slightly less defined muzzle shapes, slightly blurrier collarbones, and a little less consistency on outline styles. Eyes are usually a bit less detailed but the eyes were already often weird so sometimes being more vague turns out better.
And this is very subjective but with less than 20 tags, it's more likely to fill in with odd choices; e.g. if I have it generate a cat in a dress, I could get a cat in a dress and also in a collared shrug that I've never seen anywhere before and looks like someone tailored a suit jacket way too short.
Everything is set up as instructed, but all generated images are just the classic green splotches. Config file (as provided on the page) is the same name as the checkpoint file, and placed in the same folder. What else could be wrong?
is it still possible to have a create option so i can still use the LORA on civitai or no?
Details
Files
fluffyUniverseFurry_fluffyUniverse10.yaml
Mirrors
fluffymix_v20.yaml
fluffyUniverseFurry_v21Vpred.yaml
fluffymix_v10.yaml
fluffyUniverseFurry_fluffyUniverse10.yaml
easyfluff_v81.yaml
easyfluff_v10Prerelease.yaml
fluffyUniverseFurry_v20Vrped.yaml
hyperfusionVpred_v9Vpred.yaml
arymARandomYiffMix_v20.yaml
fluffymix_v40.yaml
easyfluff_v6.yaml
fluffymix_v30.yaml
easyfluff_v9.yaml
fluffyUniverseFurry_v20PrunedVpred.yaml
easyfluff_v7.yaml
fluffyrockUnfluffed_v10.yaml
adhdmix_v10.yaml