cascade_stage_c_anime_finetune■The descriptions for Dora and the checkpoints are provided within each tab. You’ll also find tips on training and inference, as well as uploaded workflows in each tab, so feel free to take a look if you’re interested.I would like to share the possibilities of cascade with everyone.My wish is for many people to discover basemodels with potential and to see their possibilities unfold even further. I would be happy if I can help make that happen.Cascade generates visually appealing images similar to professional artwork and photography, with high expressive flexibility.I believe that this quality is not derived from the model’s parameter count or architecture but rather from more fundamental aspects, such as the creator’s aesthetic vision and the overall completeness of the model’s training.Their aesthetic is universal and never fades. There may be models with specifications superior to Cascade, but its artistry is unique—transcending mere specs—and continues to shine.Moreover, Cascade’s lightweight, flexible, single-TE architecture is close to my ideal, and its repository transparency is higher than that of major models. I have great respect for the developers’ efforts in providing such a wonderful model.Thanks to its efficient compression rate, the training burden is also reduced.Please be careful as sexual images are also generated.I also have some merged models for SD1.5 i2i, so feel free to use them as a reference. They come in three styles—anime, realistic, and Asian—so you can choose whichever you like.<a target="_blank" rel="ugc" href="https://civarchive.com/models/1246353?modelVersionId=2211233">https://civarchive.com/models/1246353?modelVersionId=2211233</a>Cascades have potential.My dream is to see more Cascade models. I'd love to see the models you've trained as well!If you have any questions, please feel free to ask!日本語での質問も大丈夫ですのでご気軽にお声がけください～

cascade_lab

cascadeLab_v00.safetensors

cascadeLab_v00_trainingData.zip

Files with SHA256: 17ac73399d2649f444252bdcf97cc1e7e248487e490494b0b41690d6ec854d7f