JohnnyRacer

How to use docker image to manually build manylinux wheel

1

Hi, Ive pulled the manylinux2014 docker image from quay.io and would like to manually build manylinux wheels, but when I use docker exec to run python3.8 -m build. The packages...

I've had no problems converting the official FFHQ checkpoints but couldn't convert BRECAHAD checkpoints due to the error below. It kept mentioning `torch_utils` being not found on line 236, but...

Working code for CPU inference?

4

Hi, I want to run inference on the CPU on Colab but I think I will have issues with the .cu CUDA extensions since there is no nvcc avaliable on...

Hi, for multi GPU training my GPU0 is using significantly more VRAM and power than GPU1, is this normal or is there someway to balance the load? 

Converted rosinality checkpoints missing discriminator weights.

1

Hi, is there a way I can convert ada pkl checkpoints to rosinality pt checkpoints with both the generator and discriminator? I'm only getting the g_ema weights in my converted...

Text encoder still not working correctly with LoRa Dreambooth training script

28

Hello, I am getting much better results using the `--train_text_encoder` flag with the Dreambooth script. However, the actual outputed LoRa `.pt` files from models trained with `train_text_encoder` gives very bad...

Images are the wrong size (256px for stable diffusion 1.5) after using ckpt to diffusers script

3

### Describe the bug Hello, I was testing [the conversion script for ckpts to diffusers](https://raw.githubusercontent.com/huggingface/diffusers/039958eae55ff0700cfb42a7e72739575ab341f1/scripts/convert_original_stable_diffusion_to_diffusers.py), when I realized all the images that generated by the converted models are only 256x256...

CUDA Error when fine tuning GPT-J for CasualLM

6

Hello, I am trying to finetune GPT-J for text generation by adapting [this notebook](https://colab.research.google.com/drive/1jCkpikz0J2o20FBQmYmAGdiKmJGOMo-o?usp=sharing). However, when I run `trainer.train` I get a CUDA error that states the following, ` RuntimeError:...

### Is your feature request related to a problem? Please describe. Hello, it seems like there is no way to disable the running code by default when returning responses which...

I am currently trying to obtain a cropped image from a canvas element. I have tried to update the code to work with a canvas instead of the standard img...