OneTrainer

OneTrainer copied to clipboard

Conditional dropout means the prompt or caption on the training image is dropped, and the caption is "blank". The theory is this can help with unconditional guidance, per the original...

Curlypla

When finetune+vae enabled, onetrainer uses sample prompt as file name. Works fine for finetune only.

1

``` FileNotFoundError: [Errno 2] No such file or directory: 'woman, brunette' Error during sampling, proceeding without sampling Traceback (most recent call last): File "C:\PhotoVideo.AI\OneTrainer\modules\trainer\GenericTrainer.py", line 242, in __sample_loop self.model_sampler.sample( File...

maximkr

when I try to convert PixArt safetensors to Diffusers or PTH to diffuser or diffuser to safetensors the app closes, anything i am not doing correctly ?. below is the...

7sanal7san

It would be very useful to have a way to know if the currently training epoch is training the text encoder.

driqeks

As the title says. It would be lovely to get a estimated completion time printed out somewhere. In GUI or the terminal. Something as simple as epoch time x total...

Tr1dae

Using the UI with the setting attached (--debug-mode --cache-only). The "Stop Training" button on the UI does not stop writing out debug images. Ctrl-C on the terminal also doesn't stop...

dioxic

Is it compatible with linux?

9

how do i deal with this on a rented linux gpu 

sneccc

IoError(Os { code: 5, kind: PermissionDenied, message: "Access is denied." })

8

Interestingly the saves worked in `G:\OneTrainer\workspace\save` But model output destination failed while saving `G:/automatic1111/stable-diffusion-webui/models/Stable-diffusion/one_train`   

FurkanGozukara

Add support for SSD-1B

3

Hi, is it possible to add support for the segmented SDXL model? https://huggingface.co/segmind/SSD-1B

nikitabalakin

This repository supports the VAE training feature. But is it possible to add support for training LCM as a VAE decoder? This is a recently published feature by openai. This...

dill-shower