NicolasNerr

Hello, Thank you for the good work. Please can you work toward doing a good documentation for this repo ? Some arguments are not clearly defined, and it's not clear...

segmentation fault core dumped

2

Hi ! Thank you for such great videos and the code ! I happen to have a "segmentation fault error (core dumped)" "The segfault happens while pytorch was trying to...

How to train on custom dataset without text prompts and class conditionning

34

Hello, I want to apply Latent Diffusion Model to medical images data. How can I feed training images from a directory of .jpg files to the train the diffusion model...

minimal number of samples for stable training -> some issue

3

Hi ! I was wondering if some people tested the diffusion training process with few images ( 1000 or less) and obtained good results ? I am working with rare...

Strange color shifts for custom data (histopathology images)

10

Hello, I am using the repo to produce synthetic histopathology images. However, I am observing a weird color shift during training. As training progress, this shift is getting worst and...

Super Res

1

Hello, I am not sure of how to use the super resolution training ? What kind of dataset does it need ? Thank you so much

saving checkpoints frequency

1

Hello, Is there a possibility to observe samples let's say every 1K steps to monitor training ? Thank you

EMA sampling produces only noise

9

Hi, I am training on a dataset of 500 images (I know it's not a lot), with diffusion steps=4000 and basic parameters proposed in the read me. Using the first...