Photo realistic mix (majority Asian girls). To use with my loras. Recommended sampler Euler, 2M Karras, &amp; Restart. v3.5: Cleaner background and model. Need new M35 specific Lora for best result. v2.4: Ease of use &amp; realism somewhere in the middle. Better background and generic model. v2.2: Harder to use, more photographic look, less perfect, more realism. v1.4: Easier to use, more details. Recommended for beginners. More idols and newer version Loras also available at <a target="_blank" rel="ugc" href="https://ko-fi.com/makina69">https://ko-fi.com/makina69</a> Training Tips with v3.5 30 images = 35 repeats. 40 = 30 reps 50 = 25 reps mixed_precision = "fp16"clip_skip = 2max_train_epochs = 6 (Epoch 4, 5 or 6 should be the best)[general_args.dataset_args]resolution = 768batch_size = 2 [network_args.args]network_dim = 128network_alpha = 64.0min_timestep = 0max_timestep = 1000 [optimizer_args.args]optimizer_type = "AdamW"lr_scheduler = "cosine"learning_rate = 0.0001unet_lr = 0.0001text_encoder_lr = 5e-5min_snr_gamma = 5

Makina Mix

Added more realism, less AI like than v1.4. But harder to use

Files with SHA256: 4dd48b8c50c9f42a613bd235dbbb5ee1241e71290a1db61a98582c979247bc16