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 (17)
Strange, I have v2.0 generating only green dots on a black background.
Download the configs, and put it in the same folder as the model.
@deygdrixe221 I notice that there's a separate configs folder in ComfyUI. Should the .yaml go in this folder or the checkpoint folder?
That's strange even though I putted the config file next to the model in the same folder for 2.0 pruned model (I'm using google colab for it) when I generate images it look all okay but when I use my lora model to generate everything looked blurry and it's odd? 1.0 no problems on lora but 2.0 confused me
What model was your LORA trained on?
@deygdrixe221 can we discuss this more on discord better so that we don't overflow the messages here?
@deygdrixe221 even though I trained my lora on this same exact model? Is there something that affected the config file?
@francot1999420 I've been dealing with the problem for quite some time. In fact, the instructions were on the official page of the model. I'm a complete idiot.)) When training models based on FluffyRock, you must enable the parameterization "v parameter". The setting is located right on the start page when selecting the basic model.
@deygdrixe221 you sure the v parameter thing to use on lora training with this model is the only problem to fix or something missing to fix as well?
@francot1999420 Absolutely. I had the same problem. I read about this parameter on the FluffyrRock homepage. You've probably seen how many models I already have. Now imagine me having to train it all over again. ))))
@deygdrixe221 should I wait for an update on a new version of this model in order to work or I use this model for lora training with that v parameter to see if it worked?
@francot1999420 All my FluffyRock mixes are trained with this parameter, starting with version 2.0.
@deygdrixe221 So I guess I'll train the lora but this time with the v parameters and if it didn't worked well... idk
@francot1999420 Try it, it worked for me. Literally trained the characters from the Darkwing Duck cartoon. Tightened up the style many times better, I'll be posting this model soon as well.
@deygdrixe221 Okay I'll try later and thanks for coming back to respond to me since it's been a month the last time you messaged me for help heh. Do you have discord or not just saying if you like to chat more? : )
@francot1999420 I usually have little time and a lot of work. Plus, I don't speak English well. ))
@deygdrixe221 I mean mostly texting not calling heh
Details
Files
fluffyUniverseFurry_v20PrunedVpred.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