these models shouldn't be used, it's about a private testing of different training parameters.I can't prevent you from downloading it =(Maybe in the future I will change this to a public space with more info to help people to train Flux D

it's_a_test

accelerate launch "./sd-scripts/flux_train_<a target="_blank" rel="ugc" href="http://network.py">network.py</a>" ^--pretrained_model_name_or_path "D:\kohya_ss\flux\unet\flux1DevFp8_v10.safetensors" ^--clip_l "D:/stable-diffusion-webui-forge-main/models/text_encoder/flux/clip_l.safetensors" ^--t5xxl "D:/stable-diffusion-webui-forge-main/models/text_encoder/flux/flux1T5TextEncoder_stock.safetensors" ^--ae "D:/stable-diffusion-webui-forge-main/models/VAE/flux/flux1DevVAE_stock.safetensors" ^--train_data_dir "D:\kohya_ss\flux\img" ^--output_dir "D:/kohya_ss/flux/models/whimsical_flux5" ^--output_name "whimsical_flux5" ^--save_model_as safetensors ^--sdpa ^--persistent_data_loader_workers ^--max_data_loader_n_workers 2 ^--seed 777 ^--gradient_checkpointing ^--mixed_precision bf16 ^--save_precision fp16 ^--network_module networks.lora_flux ^--network_dim 24 ^--network_alpha 24 ^--network_args train_blocks=single rank_dropout=0.1 module_dropout=0.1 ^--optimizer_type lion ^--lr_scheduler cosine ^--learning_rate 3e-4 ^--network_train_unet_only ^--timestep_sampling sigmoid ^--model_prediction_type raw ^--guidance_scale 1.0 ^--loss_type l2 ^--resolution 768,768 ^--cache_text_encoder_outputs ^--cache_text_encoder_outputs_to_disk ^--fp8_base ^--enable_bucket ^--bucket_no_upscale ^--split_mode ^--prior_loss_weight 1.0 ^--caption_extension .txt ^--keep_tokens 0 ^--network_dropout 0.1 ^--max_grad_norm 1.0 ^--min_snr_gamma 10 ^--save_every_n_epochs 1 ^--train_batch_size "2" ^--multires_noise_iterations 6 ^--multires_noise_discount 0.3 ^--optimizer_args weight_decay=0.4 betas="[0.95, 0.98]" ^--max_train_epochs 30 ^--enable_wildcard

Files with SHA256: 6f8d42e73e0ba87ef4eda467032b2fed276e68015c3b8202288afa0997450399