<h2 id="heading-8">This model works correctly only with <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/189669?type=Config">config file</a>. Place this file in the same folder as this model.</h2>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. <a target="_blank" rel="ugc" href="https://civarchive.com/models/92527/fluffyrock-pre-3m-autocomplete">Tag Autocomplete File</a> - courtesy of FluffyRock's tag database. This model is universal and suitable for generating a variety of objects, including realism.<h2 id="heading-6"> I express special gratitude to each author of the listed models present in my mix.</h2><h2 id="heading-7"> LORA training on models with the FluffyRock base includes the following instructions:</h2><ol><li>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 warning</li><li>it is advisable to use the parameter "noise_offset" around 0.1-0.9.</li></ol><h2 id="heading-13"> Reminder</h2>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.

Fluffy Universe (Furry)

Furry DreamShape is my personal staple mix that I update to suit my needs, and I do LORA training on it as well. When installing this Furry DreamShape, do not forget to install the configuration files that must be placed in the folder with this model.After figuring out the settings, I was able to combine the EasyFluff model with my existing merge. The results were incredible. Many flaws such as "burning colors" were corrected, and the overall level of detail increased significantly. Since EasyFluff is by far the model with the largest dataset, I will be building my model on its basis in the future. As for the rest of the description, this model also includes BB95, some anime models, YiffMix, and Dreamshape. In the future, if there will be updates to the main custom models, like the previously mentioned Dreamshape, my model will also be updated. The same goes for the main EasyFluff model. As for the recommended samplers, I almost always use the latest DPM++ 3M SDE, experimenting with their subspecies. All the tags specified in the YiffMix and FluffyRock datasets work on this model as well.

Files with SHA256: 7fc79a2e0665cf40c4d7cc2bc39ae4b9a06ad83197eb7daf872d013f8daf02d6