setothegreat

Can confirm this. On my 3090 I can only generate a single image with the hires fix before I get an OOM error when trying to generate any more images...

Any updates on this?

> Just to make sure I understand, is this considered implemented because the extension already allows us to mix and match multiple models together (and even mix T2i with ControlNet...

Just got this error last night when training a LoRA, hadn't happened with the LoRAs I'd trained prior. Search on Google revealed that it's the result of one of the...

Not sure if it's an error but I'm having the issue where resuming the model training seems to load everything up successfully, but the training steps are reset back to...

> PS: I am not quite sure that `min_snr_gamma=5` would work well for the Flux training ,but it seemed to be a little bit improvement for the convergence Have you...

Can't confirm this with my own finetune (note: wasn't trained on latest update) using ComfyUI, as increasing the CFG just results in a lower image quality. That being said, I...

`accelerate launch --mixed_precision bf16 --num_cpu_threads_per_process 1 flux_train.py --pretrained_model_name_or_path D:\FluxKohya\sd-scripts\models\flux1-dev.sft --clip_l D:\FluxKohya\sd-scripts\models\clip_l.safetensors --t5xxl D:\FluxKohya\sd-scripts\models\t5xxl_fp16.safetensors --ae D:\FluxKohya\sd-scripts\models\ae.sft --save_model_as safetensors --sdpa --persistent_data_loader_workers --max_data_loader_n_workers 2 --seed 44 --gradient_checkpointing --mixed_precision bf16 --save_precision bf16 --dataset_config D:\FluxKohya\sd-scripts\fluxdataset.toml...