Mister K comments

Results 31 comments of


                                            Mister K

Best Code for Full SDXL finetuning?

``` 0: 640x448 1 face, 15.9ms Speed: 2.8ms preprocess, 15.9ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 448) Using pytorch attention in VAE Using pytorch attention in...

Error handling request Traceback (most recent call last): File "/home/ks/venv/lib/python3.12/site-packages/aiohttp/web_protocol.py", line 477, in _handle_request resp = await request_handler(request)

mmmmm, i git clone comfyui into another folder instead... and check if it runs... which it did... so it's not related to any other dependencies. but when i ran micro...

I had a hard time using ComfyUI on Windows 11 previously... so this is what I changed...

![Screenshot 2024-09-14 212805](https://github.com/user-attachments/assets/787cf0c0-bfbc-4fdc-96c2-6bf466321132) ![Screenshot 2024-09-14 213505](https://github.com/user-attachments/assets/f86ecdfb-5319-43ef-b12c-63528a764225) but... since i technically have a linux machine now, i can technically get flash attention 2 running. even though it is not supported in...

I had a hard time using ComfyUI on Windows 11 previously... so this is what I changed...

![Screenshot 2024-09-14 215737](https://github.com/user-attachments/assets/307030ca-477c-4db9-bc93-a26264359e4a) okay. so first issue that i encounter is the following: ``` [START] Security scan DEPRECATION: Loading egg at /home/ks/comfy/venv/lib/python3.12/site-packages/flash_attn-2.6.3-py3.12-linux-x86_64.egg is deprecated. pip 24.3 will enforce this behaviour...

I had a hard time using ComfyUI on Windows 11 previously... so this is what I changed...

from the rest of the startup process... i can't actually tell if there's any difference... i just wish i can figure out how to get rid of all the warnings......

I had a hard time using ComfyUI on Windows 11 previously... so this is what I changed...

![image](https://github.com/user-attachments/assets/39262011-7e8c-42f0-9e90-626724d777ec) Okay i am in the process of installing flash attention on my windows 11 pc ``` ddd insightface ven Sat Oct 26 17:29:25 2024 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 560.35.03 Driver...

I had a hard time using ComfyUI on Windows 11 previously... so this is what I changed...

![image](https://github.com/user-attachments/assets/895711bd-85ce-4158-bb57-9a1fc3e2034c) the other window is still installing flash-attn as i type this. let's see if it makes any difference once it is installed... i am assuming once it is installed...

I had a hard time using ComfyUI on Windows 11 previously... so this is what I changed...

![image](https://github.com/user-attachments/assets/967d5bb7-2dda-4794-8226-b3a2e92b166b) You are kidding me right? that's all i got to do and now my image generation based on my existing workflows... wiithout any other special modification... from the normal...

I had a hard time using ComfyUI on Windows 11 previously... so this is what I changed...

``` ddd insightface ven Sat Oct 26 19:08:12 2024 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 560.35.03 Driver Version: 565.90 CUDA Version: 12.7 | |-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile...

I had a hard time using ComfyUI on Windows 11 previously... so this is what I changed...

https://huggingface.co/microsoft/Phi-3-mini-4k-instruct from MS's hugging face it mentioned briefly. **_flash_attn==2.5.8 _** below i have updated to show my current flash-attn built from source after installing via pip. ``` How to Use...