diffusers

diffusers copied to clipboard

Dreambooth Training not reading instance data

5

### Describe the bug I am trying to run the Dreambooth Training on my local device from the line command. However, this gave me a hard time due to the...

asahi0130

Dreambooth runs, but doesn't train model or generate class images

9

### Describe the bug My Diffusers is running but it just doesn't want to train a model based on my settings and I don't know why. It also does not...

AIRenaissance

Hey Shivam! I've been going around this morning trying to contact other Dreambooth developers with the goal of maybe putting together a team to work on ONE unified dreambooth training...

d8ahazard

Different output on local machine gpu 3060

7

### Describe the bug When I train the notebook on colab it output good result similar to the images I trained on But when I trained it on my local...

AhmedAbdellaa

Prompt per image best practice

5

Not exactly a feature request but when I try to submit a blank issue it takes me to the huggingface diffusers issues, want to ask here. Just wondering about this...

rmac85

### Describe the bug New alerts appear after training, that were not there even a few days ago. These are the alerts: ``` 2023-02-11 07:34:06.889857: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary...

shadowlocked

This is more of a question than request... I notice train_dreambooth.py has two different schedulers, a pipeline scheduler and noise scheduler, wondering if these two schedulers are reading from the...

rmac85

I want to train the model to learn multiple identifiers, for example: swy dog is playing with sks cat While so far not very successful on the training results, I...

wyang22

### Describe the bug I'm training locally with 8GB vram card. To make training faster, I have changed in the settings, gradient_accumulation_steps from 1 to 16, also I run "accelerate...

a-l-e-x-d-s-9

[launch_inpaint.sh] AttributeError: 'LatentsDataset' object has no attribute 'class_images_path'

2

### Describe the bug  **My launch_inpaint.sh** export LD_LIBRARY_PATH=/usr/lib/wsl/lib:$LD_LIBRARY_PATH export MODEL_NAME="runwayml/stable-diffusion-inpainting" export INSTANCE_DIR="training" export OUTPUT_DIR="my_model" accelerate launch train_inpainting_dreambooth.py \ --pretrained_vae_name_or_path="stabilityai/sd-vae-ft-mse" \ --pretrained_model_name_or_path=$MODEL_NAME \ --instance_data_dir=$INSTANCE_DIR \ --output_dir=$OUTPUT_DIR \ --instance_prompt="Greyalieninpa" \ --resolution=512...

ZeroCool22