Software Engineering Courses (SECourses)•12mo ago

please let me know once published

Zono50•1/29/25, 3:02 AM

@Furkan Gözükara SECourses How do i run your sana installation in arch linux?

Zono50•1/29/25, 3:03 AM

i keep getting Traceback (most recent call last):
File "/mnt/Backup_2.73TB/AI/Sana/Sana/app/app_sana.py", line 204, in <module>
pipe = SanaPipeline(args.config)
File "/mnt/Backup_2.73TB/AI/Sana/Sana/app/sana_pipeline.py", line 77, in init
config = pyrallis.load(SanaInference, open(config))
TypeError: expected str, bytes or os.PathLike object, not NoneType
Invalid number of options.

when i run app_sana.py

Zono50•1/29/25, 3:03 AM

i'm using python 3.10.15

Zono50•1/29/25, 3:04 AM

if i run the secourses and try to generate, it says it's missing yml files -

Error loading model: [Errno 2] No such file or directory: 'configs/sana_config/1024ms/Sana_1600M_img1024.yaml'

Aikage•1/29/25, 3:24 AM

Is NL prompting useful for SDXL based architecture LoRA training? ie. Illustrious? does the architecture matter since you're essentially giving it new information via the captions?

Aikage•1/29/25, 3:25 AM

I guess I will find out, I have an uncaptioned lora i will try to use joycaption on and also the built in caption tool in one trainer and i'll compare

Aikage•1/29/25, 3:26 AM

the built in uses the ....i forget i keep wanting to call it WD40

the booru type tag captions

FFurkan Gözükara SECourses please let me know once published

404_error•1/29/25, 8:36 AM

Ok np

ZZono50 <@205854764540362752> How do i run your sana installation in arch linux?

Furkan Gözükara SECoursesOP•1/29/25, 1:12 PM

hi my runpod installer should work

Furkan Gözükara SECoursesOP•1/29/25, 1:12 PM

but you need to have requirements

Furkan Gözükara SECoursesOP•1/29/25, 1:13 PM

it looks like you have error at paths

Pedrox1kk•1/29/25, 1:29 PM

There is some script to comfyUi + SVRF to runpod? @Furkan Gözükara SECourses

art-ai_usa-girl•1/29/25, 2:13 PM

this would be nice YuE: Open Music Foundation Models for Full-Song Generation https://huggingface.co/spaces/fffiloni/YuE

YuE - a Hugging Face Space by fffiloni

Zono50•1/29/25, 2:14 PM

@Furkan Gözükara SECourses any websites with galleries of videos we can use for live portrait?

PPedrox1kk There is some script to comfyUi + SVRF to runpod? <@205854764540362752>

Furkan Gözükara SECoursesOP•1/29/25, 3:42 PM

i don thave SVRF

Aart-ai_usa-girl this would be nice YuE: Open Music Foundation Models for Full-Song Gener...

Furkan Gözükara SECoursesOP•1/29/25, 3:42 PM

i was reading it right now :d

ZZono50 <@205854764540362752> any websites with galleries of videos we can use for live...

Furkan Gözükara SECoursesOP•1/29/25, 3:43 PM

not that i know

coreai•1/29/25, 5:13 PM

hello

Ccoreai hello

Furkan Gözükara SECoursesOP•1/29/25, 10:08 PM

hello

Aikage•1/30/25, 5:57 PM

just wanted to say thanks for the batch image captioning software. Took a few tries to find the best way to remove tags: "tagname, " instead of "tagname" but it's a real lifesaver vs. going through one by one and slowly deleting words

AAikage just wanted to say thanks for the batch image captioning software. Took a few t...

Furkan Gözükara SECoursesOP•1/30/25, 7:08 PM

awesome. yes it takes few tries to understand fully

art-ai_usa-girl•1/31/25, 2:55 PM

VisoMaster (Formerly Rope-next) https://github.com/visomaster/VisoMaster

Rakia Ben Sassi•1/31/25, 6:26 PM

https://youtu.be/KfC-3ndpzaM

YouTubeRakia Ben Sassi | TekForge

How AI Bias Almost Cost Me a Job: My Shocking Interview Experience

In this eye-opening video, I share my shocking job interview experience that exposed the hidden flaws in hiring algorithms. An AI system made a biased decision, misrepresenting my identity and raising serious questions about fairness in technology.

Accuracy, transparency, and security in AI systems aren’t just buzzwords—they’re the foundation o...

404_error•1/31/25, 10:36 PM

@Furkan Gözükara SECourses Hey,

As agreed several days ago, I remind you the release of VisoMaster by the creator of Rope Next

https://github.com/visomaster/VisoMaster?tab=readme-ov-fil

GitHub

GitHub - visomaster/VisoMaster: Powerful & Easy-to-Use Face Swappin...

Powerful & Easy-to-Use Face Swapping and Editing Software - visomaster/VisoMaster

Aart-ai_usa-girl VisoMaster (Formerly Rope-next) https://github.com/visomaster/VisoMaster

Furkan Gözükara SECoursesOP•1/31/25, 10:36 PM

nice ty

4404_error <@205854764540362752> Hey, As agreed several days ago, I remind you the relea...

Furkan Gözükara SECoursesOP•1/31/25, 10:36 PM

nice

Weatherby•2/1/25, 9:31 PM

Has anyone tried to run SUPIR to upscale a batch of images on something larger than a 4090? I was thinking of an A6000, as on the 4090 I managed 13 images in 4 hours, so I was thinking that with 48 I could do more than 1 image at a time or even disable some of the vram saving options to help accelerate without loosing quality?

Aikage•2/2/25, 3:30 AM

is there any way to set top k val with segment in swarm

Aikage•2/2/25, 3:30 AM

so it stops changing every face in the image

Aikage•2/2/25, 3:34 AM

oh hahahaha

Aikage•2/2/25, 3:34 AM

as always

Aikage•2/2/25, 3:35 AM

Just have to follow this guy and you always get your answer

Aikage•2/2/25, 3:44 AM

oh but they never really implemented it? I don't have any sorting in regional prompting and if I didn't download the yolo model that feature is not well explained at all think

interesting

ᴏ

ᴏᴍɴɪ•2/2/25, 9:16 PM

@Furkan Gözükara SECourses Im getting black screen when using the Flux fill dev. Any idea why its not creating the rest of image. The image is 1028 x 1028 I notice when I do use a init the ratio goes to 1536x1536