Turbo LoRA trained on preview3. Use CFG 1 and 8-12 steps. Works well on other Anima checkpoints. You can decrease the LoRA strength a bit below 1 for more variety.
Work in progress. Increases stability, anatomy, and style consistency. Details are a bit worse than base.
Model dicetak ulang dari: https://civitai.com/models/2560840
Model yang dicetak ulang hanya untuk tujuan komunikasi dan pembelajaran, bukan untuk penggunaan komersial. Penulis asli dapat menghubungi kami untuk mentransfer model melalui saluran Discord kami --- #claim-models.
