Trained Lora with Pony DiffusionNote: strength should be between 0.4 - 0.6 for better resultsimages were generated with DuchaitenJourney Model and Realistic Vision V6.0 B1(soon)Recommended configurationModel: CyberealisticPonyLORA Strength: 0.8- 1Embedding: Fast NegativeVAE: vae-ft-mse-840000-ema-prunedSampling Method: DPM++ 2M KarrasSteps: 20-25CFG: 9-10Clip Skip: 1Upscale: 4x-UltraSharpUST: 39RNI: 0.5This configuration gives as results looks like face but only in this model, working in a new version for other models

Files with SHA256: 99376ce90b3a20b8b681ac9c52ada41de3561b59c30bad2cb68758e13a0b8de1