Anh (Luka) Pham

Always get the Cuda Out Of Memory error when training LoRA despite fixing the batch_size

2

Here is my logs: **STARTIG JOB WITH CONFIG:** adaptive_loss_weight: null allow_tf32: true backup_every: 1000 batch_size: 4 bucketeer_random_ratio: 0.05 captions_getter: null checkpoint_extension: safetensors checkpoint_path: output clip_image_model_name: openai/clip-vit-large-patch14 clip_text_model_name: laion/CLIP-ViT-bigG-14-laion2B-39B-b160k dataset_filters: null...

The results of LoRA are very bad, where did I go wrong?

12

I have trained LoRA several times with faces but it seems the model can't learn anything. My dataset is as follow: ``` data.tar |- 0000.jpg |- 0000.txt ("a photo of...

Error when running on A100 Replicate

3

I tried several machine on Replicate (https://replicate.com/). My scripts work well on A40 GPU, also in Runpod it works well. But when I switch to A100 on Replicate playground, it...

ELLA cannot work with dreambooth checkpoint

2

Hi, has anyone successfully run inference with ELLA for a dreambooth checkpoint. It seems that the ELLA text encode destroys the identifier token (ohwx, sks, ...), so it could not...