Open Daniel70-liu opened 1 month ago
Hello everyone, I would like to ask how to solve the following error. I am very grateful for every suggestion.
I downloaded fluxgym manually,because the automatic flux-dev download was stuck, I manually downloaded it at the URL below: https://huggingface.co/cocktailpeanut/xulf-dev/tree/main
then ae and clip are automatically downloaded after pressing training.
Error log: [2024-10-19 12:26:33] [INFO] Running F:\Daniel\fluxgym\outputs\caicai\train.bat [2024-10-19 12:26:33] [INFO] [2024-10-19 12:26:33] [INFO] (fluxgym) F:\Daniel\fluxgym>accelerate launch --mixed_precision bf16 --num_cpu_threads_per_process 1 sd-scripts/flux_train_network.py --pretrained_model_name_or_path "F:\Daniel\fluxgym\models\unet\flux1-dev.sft" --clip_l "F:\Daniel\fluxgym\models\clip\clip_l.safetensors" --t5xxl "F:\Daniel\fluxgym\models\clip\t5xxl_fp16.safetensors" --ae "F:\Daniel\fluxgym\models\vae\ae.sft" --cache_latents_to_disk --save_model_as safetensors --sdpa --persistent_data_loader_workers --max_data_loader_n_workers 2 --seed 42 --gradient_checkpointing --mixed_precision bf16 --save_precision bf16 --network_module networks.lora_flux --network_dim 4 --optimizer_type adamw8bit --sample_prompts="F:\Daniel\fluxgym\outputs\caicai\sample_prompts.txt" --sample_every_n_steps="760" --learning_rate 8e-4 --cache_text_encoder_outputs --cache_text_encoder_outputs_to_disk --fp8_base --highvram --max_train_epochs 16 --save_every_n_epochs 4 --dataset_config "F:\Daniel\fluxgym\outputs\caicai\dataset.toml" --output_dir "F:\Daniel\fluxgym\outputs\caicai" --output_name caicai --timestep_sampling shift --discrete_flow_shift 3.1582 --model_prediction_type raw --guidance_scale 1 --loss_type l2 [2024-10-19 12:26:33] [INFO] 'accelerate' O Υ~ R O B i 檺 { Χ妸 ɡC [2024-10-19 12:26:33] [ERROR] Command exited with code 1 [2024-10-19 12:26:33] [INFO] Runner:
file.txt
Hello everyone, I would like to ask how to solve the following error. I am very grateful for every suggestion.
I downloaded fluxgym manually,because the automatic flux-dev download was stuck, I manually downloaded it at the URL below: https://huggingface.co/cocktailpeanut/xulf-dev/tree/main
then ae and clip are automatically downloaded after pressing training.
Error log: [2024-10-19 12:26:33] [INFO] Running F:\Daniel\fluxgym\outputs\caicai\train.bat [2024-10-19 12:26:33] [INFO] [2024-10-19 12:26:33] [INFO] (fluxgym) F:\Daniel\fluxgym>accelerate launch --mixed_precision bf16 --num_cpu_threads_per_process 1 sd-scripts/flux_train_network.py --pretrained_model_name_or_path "F:\Daniel\fluxgym\models\unet\flux1-dev.sft" --clip_l "F:\Daniel\fluxgym\models\clip\clip_l.safetensors" --t5xxl "F:\Daniel\fluxgym\models\clip\t5xxl_fp16.safetensors" --ae "F:\Daniel\fluxgym\models\vae\ae.sft" --cache_latents_to_disk --save_model_as safetensors --sdpa --persistent_data_loader_workers --max_data_loader_n_workers 2 --seed 42 --gradient_checkpointing --mixed_precision bf16 --save_precision bf16 --network_module networks.lora_flux --network_dim 4 --optimizer_type adamw8bit --sample_prompts="F:\Daniel\fluxgym\outputs\caicai\sample_prompts.txt" --sample_every_n_steps="760" --learning_rate 8e-4 --cache_text_encoder_outputs --cache_text_encoder_outputs_to_disk --fp8_base --highvram --max_train_epochs 16 --save_every_n_epochs 4 --dataset_config "F:\Daniel\fluxgym\outputs\caicai\dataset.toml" --output_dir "F:\Daniel\fluxgym\outputs\caicai" --output_name caicai --timestep_sampling shift --discrete_flow_shift 3.1582 --model_prediction_type raw --guidance_scale 1 --loss_type l2 [2024-10-19 12:26:33] [INFO] 'accelerate' O Υ~ R O B i 檺 { Χ妸 ɡC [2024-10-19 12:26:33] [ERROR] Command exited with code 1 [2024-10-19 12:26:33] [INFO] Runner:
file.txt