ModelsLab/Sagging [Flux] - V0.4.22

Images: 32Captions: natural languageEpoch 30 · Steps: 5280 · Loss: 0.263Trigger words: -Repeat: 11Epoch: 30Save Every N Epochs: 2Clip Skip: 1Text Encoder learning rate: 0.00001Unet learning rate: 0.00008LR Scheduler: constant_with_warmupOptimizer: AdamW8bitNetwork Dim: 16Network Alpha: 8Gradient Accumulation Steps: 2Noise Offset: 0.03Multires noise Discount: 0.1Multires noise iterations: 10conv_dim: -conv_alpha: -Batch Size: -Sampler: euler