subprocess.CalledProcessError: Command '['E:\\kohya_ss\\venv\\Scripts\\python.exe', 'E:/kohya_ss/sd-scripts/flux_train_network.py', '--config_file', './test/output/config_lora-20240822-182849.toml']' returned non-zero exit status 3221225477.

[CNEA-lw]

Complete error content: Related toml files Flux.1-dev-test-v3_20240822-182849.json My personal skills are too low, I hope you can help me solve it, thank you.

[eftSharptooth]

It was my mistake earlier, no worries. Hey, I missed it earlier, but it says accelerator device is cpu. Could you open a terminal or command prompt and paste the results when you run "nvidia-smi". It might be that your accelerator is not configured to use your gpu.

[kohya-ss]

The log says accelerator device: cpu. The accelerate config setting may be incorrect.

[eftSharptooth]

OK, so you will need to run an accelerate config in your venv. It would be good to also get your gpu info (single or multiple) and IDs if that has to be set via environmental variable. This is done with nvidia-smi in a command prompt window.

[CNEA-lw]

OK, so you will need to run an accelerate config in your venv. It would be good to also get your gpu info (single or multiple) and IDs if that has to be set via environmental variable. This is done with nvidia-smi in a command prompt window.

Thank you for your help. After I reset the accelerator device related issues on the startup page, I can indeed train. Thank you for your help!

[CNEA-lw]

The log says accelerator device: cpu. The accelerate config setting may be incorrect.

Thank you for your help. After I reset the accelerator device related issues on the startup page, I can indeed train. Thank you for your help!

[CNEA-lw]

If you encounter related problems, please 5. (Optional) Manually configure Accelerate after starting the setup Perform a reset.

[eftSharptooth]

Im glad you are working! Happy training and good luck!

[8bit-boom]

I have similar problem, already tried Manually configure Accelerate, but it didn't help.

config file: "LoRA_type": "Flux1", "LyCORIS_preset": "full", "adaptive_noise_scale": 0, "additional_parameters": "", "ae": "D:/SD/stable-diffusion-webui/models/VAE/ae.safetensors", "apply_t5_attn_mask": false, "async_upload": false, "block_alphas": "", "block_dims": "", "block_lr_zero_threshold": "", "bucket_no_upscale": false, "bucket_reso_steps": 64, "bypass_mode": false, "cache_latents": true, "cache_latents_to_disk": true, "caption_dropout_every_n_epochs": 0, "caption_dropout_rate": 0, "caption_extension": ".txt", "clip_l": "D:/SD/stable-diffusion-webui/models/Text Encoder/clip_l.safetensors", "clip_skip": 1, "color_aug": false, "constrain": 0, "conv_alpha": 1, "conv_block_alphas": "", "conv_block_dims": "", "conv_dim": 1, "dataset_config": "", "debiased_estimation_loss": false, "decompose_both": false, "dim_from_weights": false, "discrete_flow_shift": 1, "dora_wd": false, "down_lr_weight": "", "dynamo_backend": "no", "dynamo_mode": "default", "dynamo_use_dynamic": false, "dynamo_use_fullgraph": false, "enable_bucket": true, "epoch": 1, "extra_accelerate_launch_args": "", "factor": -1, "flip_aug": false, "flux1_cache_text_encoder_outputs": true, "flux1_cache_text_encoder_outputs_to_disk": true, "flux1_checkbox": true, "fp8_base": true, "full_bf16": false, "full_fp16": false, "gpu_ids": "", "gradient_accumulation_steps": 1, "gradient_checkpointing": true, "guidance_scale": 1, "highvram": true, "huber_c": 0.1, "huber_schedule": "snr", "huggingface_path_in_repo": "", "huggingface_repo_id": "", "huggingface_repo_type": "", "huggingface_repo_visibility": "", "huggingface_token": "", "ip_noise_gamma": 0, "ip_noise_gamma_random_strength": false, "keep_tokens": 0, "learning_rate": 0.0002, "log_config": false, "log_tracker_config": "", "log_tracker_name": "", "log_with": "", "logging_dir": "D:\SD\stable-diffusion-webui\Traning\drow\opt3\opt2\Chadra Ironwall\log", "loraplus_lr_ratio": 0, "loraplus_text_encoder_lr_ratio": 0, "loraplus_unet_lr_ratio": 0, "loss_type": "l2", "lowvram": false, "lr_scheduler": "linear", "lr_scheduler_args": "", "lr_scheduler_num_cycles": 1, "lr_scheduler_power": 1, "lr_scheduler_type": "", "lr_warmup": 0, "main_process_port": 0, "masked_loss": false, "max_bucket_reso": 2048, "max_data_loader_n_workers": 0, "max_grad_norm": 1, "max_resolution": "512,512", "max_timestep": 1000, "max_token_length": 75, "max_train_epochs": 0, "max_train_steps": 1000, "mem_eff_attn": false, "mem_eff_save": false, "metadata_author": "", "metadata_description": "", "metadata_license": "", "metadata_tags": "", "metadata_title": "", "mid_lr_weight": "", "min_bucket_reso": 256, "min_snr_gamma": 10, "min_timestep": 0, "mixed_precision": "bf16", "model_list": "custom", "model_prediction_type": "raw", "module_dropout": 0, "multi_gpu": false, "multires_noise_discount": 0.2, "multires_noise_iterations": 8, "network_alpha": 16, "network_dim": 16, "network_dropout": 0, "network_weights": "", "noise_offset": 0, "noise_offset_random_strength": false, "noise_offset_type": "Original", "num_cpu_threads_per_process": 2, "num_machines": 1, "num_processes": 1, "optimizer": "AdamW8bit", "optimizer_args": "", "output_dir": "D:\SD\stable-diffusion-webui\Traning\drow\opt3\opt2\Chadra Ironwall\model", "output_name": "Flux.sidney-sweeney-v1", "persistent_data_loader_workers": false, "pretrained_model_name_or_path": "D:/SD/stable-diffusion-webui/models/Stable-diffusion/flux_dev.safetensors", "prior_loss_weight": 1, "random_crop": false, "rank_dropout": 0, "rank_dropout_scale": false, "reg_data_dir": "", "rescaled": false, "resume": "", "resume_from_huggingface": "", "sample_every_n_epochs": 0, "sample_every_n_steps": 250, "sample_prompts": "a painting of a man wearing a funny hat, by darius kawasaki --w 832 --h 1260 --s 20 --l 3", "sample_sampler": "euler", "save_as_bool": false, "save_every_n_epochs": 1, "save_every_n_steps": 0, "save_last_n_steps": 0, "save_last_n_steps_state": 0, "save_model_as": "safetensors", "save_precision": "bf16", "save_state": false, "save_state_on_train_end": false, "save_state_to_huggingface": false, "scale_v_pred_loss_like_noise_pred": false, "scale_weight_norms": 0, "sdxl": false, "sdxl_cache_text_encoder_outputs": true, "sdxl_no_half_vae": true, "seed": 42, "shuffle_caption": false, "split_mode": false, "split_qkv": false, "stop_text_encoder_training": 0, "t5xxl": "D:/SD/stable-diffusion-webui/models/Text Encoder/t5xxl_fp16.safetensors", "t5xxl_max_token_length": 512, "text_encoder_lr": 0, "timestep_sampling": "sigmoid", "train_batch_size": 1, "train_blocks": "all", "train_data_dir": "D:/SD/stable-diffusion-webui/Traning/drow/opt3/opt2/Chadra Ironwall/image114", "train_norm": false, "train_on_input": true, "training_comment": "", "unet_lr": 0.0001, "unit": 1, "up_lr_weight": "", "use_cp": false, "use_scalar": false, "use_tucker": false, "v2": false, "v_parameterization": false, "v_pred_like_loss": 0, "vae": "", "vae_batch_size": 0, "wandb_api_key": "", "wandb_run_name": "", "weighted_captions": false, "xformers": "sdpa" }

[kohya-ss]

"pretrained_model_name_or_path": "D:/SD/stable-diffusion-webui/models/Stable-diffusion/flux_dev.safetensors",

Are you using the fp16 checkpoint? The fp8 checkpoint gives an error.

[8bit-boom]

"pretrained_model_name_or_path": "D:/SD/stable-diffusion-webui/models/Stable-diffusion/flux_dev.safetensors",

Are you using the fp16 checkpoint? The fp8 checkpoint gives an error.

I am using fp8, downloaded from civitai , they had fp32 an fp8, will try with fp16

[8bit-boom]

Its working now, thank you so much

[AlexiosDyral]

I have the same problem, but I set up my gpu and my fp16, what should I do

[AlexiosDyral]