redacted

really desperate to start uing LoRA, however I use GPTQ-4bit-32g.GGML will this be a problem?

> python convert-lora-to-ggml.py llama-oasst-lora-13B Traceback (most recent call last): File "C:\Users\pwnzr\Desktop\LLM\lora\convert-lora-to-ggml.py", line 109, in write_file_header(fout, params) File "C:\Users\pwnzr\Desktop\LLM\lora\convert-lora-to-ggml.py", line 52, in write_file_header fout.write(struct.pack("ii", params["r"], params["lora_alpha"])) struct.error: required argument is not...

it happens to me in txt2img when using lora or locon without vae, except it looks good in preview until the last step then it it one colour

> I solved it by locally removing the font. sorry I don't remember where I removed so I will share the whole file that I have in stable-diffusion-webui\scripts\test_my_prompt_custom_script.py I love...

> Fix for font error line 4 from fonts.ttf import Roboto => from modules.paths_internal import roboto_ttf_file line 38 font = ImageFont.truetype(Roboto, fontsize) => font = ImageFont.truetype(roboto_ttf_file, fontsize) > > ```python...

> If you want to release it as a Forge extension, the proper way to do so is to release the source code on GitHub so that people can know...

Hi, this is not a FORGE plugin it's a standalone Python program for extracting the UNET, the only plugin is a loader https://github.com/captainzero93/load-extracted-unet-automatic1111 please read the readme for both

As of the latest commit, they are not working for me at all, I have the correct VAE, encoder etc it appears to work fine but at the last steps...

@blakejrobinson please could you link it to me

I did in fact have the smaller file, thank you