Sagging [Flux] - V0.3.18

Dataset:Greater variety, but lower number in images, better captions, unfortunately again fragmented into tags due to the incorrect use of the onsite trainer from Tensor.art.Known issues:The subject does not always know where the front and back are. As a result, the anatomy is sometimes considerably disturbed (bottom on the knees or stomach, etc.).Due to the incorrect captioning/tagging, the people are sometimes generated too large, too small or with two buttocks.The model has also incorrectly learned to generate doors, sockets or towel rails on the wall.Stay tuned. v0.4 - v0.9 will be published within the next few hours.Images: 30 Captions: natural language, destroyed by TAEpoch 35 · Steps: 5250 · Loss: 0.228Trigger words: -Repeat: 10Epoch: 35Save Every N Epochs: 3Clip Skip: -Text Encoder learning rate: 0.00001Unet learning rate: 0.0001LR Scheduler: constantOptimizer: AdamW8bitNetwork Dim: 16Network Alpha: 16Gradient Accumulation Steps: 2Noise Offset: 0.03Multires noise Discount: 0.1Multires noise iterations: 10conv_dim: -conv_alpha: -Batch Size: -Sampler: euler