diffusers

diffusers copied to clipboard

[Feature request] Colab train inpanting dreambooth

2

Would be possible to do a Colab version of it?

Lyntai

Greetings, I saw your neural network is very and very promising, I offer to help with the development, and make even an ordinary person who does not understand anything, create...

MorugaDS

### Describe the bug The tags are listed in a text file with the same name as the image file, but the text file is mistakenly opened as an image...

Prof-Cheese

In TheLastBen dreambooth fork, you can stop the text encoder training at a specific step using:--stop_text_encoder_training=n This helps prevent overfitting, particularly when training for style transfer, this would be a...

futurevessel

Attempting to unscale FP16 gradients

1

### Describe the bug The script wouldn't start the training steps due to the error in the title ### Reproduction _No response_ ### Logs ```shell Steps: 0%| | 0/800 [00:00

cian0

Currently, there does not seem to be support for a parallelized training on multiple GPUs. As far as I know, the `from_pretrained` loading of models and pipelines should allow us...

PhilWicke

Integrate StableDiffusion Dreambooth with ColossalAI

2

**WHAT** Integrate with ColossalAI for memory/speed efficiency and improvements. **WHERE** - https://github.com/hpcaitech/ColossalAI - > Colossal-AI: A Unified Deep Learning System for Big Model Era - https://medium.com/@yangyou_berkeley/diffusion-pretraining-and-hardware-fine-tuning-can-be-almost-7x-cheaper-85e970fe207b **HOW** - https://github.com/hpcaitech/ColossalAI/tree/main/examples/images/diffusion **SEE...

0xdevalias

It would be great if you can create a UniTune implementation in free colab if you don't know what UniTune is, it's a work of google research, it's like imagic...

loboere

guide on how to run it on windows

12

can't make it run on windows natively, getting this error after running **python train_dreambooth.py** train_dreambooth.py: error: the following arguments are required: --pretrained_m odel_name_or_path, --pretrained_vae_name_or_path, --instance_data_dir maybe I'm doing something wrong?...

mhnoni

Recent change to train_dreambooth causing CUDNN_STATUS_INTERNAL_ERROR (WSL install)

1

### Describe the bug When using dreambooth in WSL Ubuntu 20.04, a recent change is causing training to fail. Undoing this single change fixes the issue on the most recent...

astrobread