Software Engineering Courses (SECourses)•2y ago

@Dr. Furkan Gözükara any chance for implementing https://github.com/plemeri/InSPyReNet or https://g

@Dr. Furkan Gözükara any chance for implementing https://github.com/plemeri/InSPyReNet or https://github.com/ZhengPeng7/BiRefNet for SD dataset image bg removal and/or masking?

GitHub

GitHub - plemeri/InSPyReNet: Official PyTorch implementation of Rev...

Official PyTorch implementation of Revisiting Image Pyramid Structure for High Resolution Salient Object Detection (ACCV 2022) - plemeri/InSPyReNet

GitHub

GitHub - ZhengPeng7/BiRefNet: [CAAI AIR'24] Bilateral Reference for...

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation - ZhengPeng7/BiRefNet

NNeo @Dr. Furkan Gözükara any chance for implementing https://github.com/plemeri/InS...

Furkan Gözükara SECourses•7/25/24, 11:03 AM

sure i can but i think they are not best

Furkan Gözükara SECourses•7/25/24, 11:03 AM

have you tested them?

Furkan Gözükara SECourses•7/25/24, 11:04 AM

RMBG is best as far as i know

Furkan Gözükara SECourses•7/25/24, 11:04 AM

this repo says they are better

Furkan Gözükara SECourses•7/25/24, 11:04 AM

https://github.com/ZhengPeng7/BiRefNet

GitHub

GitHub - ZhengPeng7/BiRefNet: [CAAI AIR'24] Bilateral Reference for...

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation - ZhengPeng7/BiRefNet

Furkan Gözükara SECourses•7/25/24, 11:04 AM

so this one looks promising

Furkan Gözükara SECourses•7/25/24, 10:34 PM

i am upgrading our app to cogvlm v2

Furkan Gözükara SECourses•7/25/24, 10:35 PM

dmn the models are like 30 40 gb

FFurkan Gözükara SECourses i am upgrading our app to cogvlm v2

Maxivi•7/25/24, 10:47 PM

any difference ?

MMaxivi any difference ?

Furkan Gözükara SECourses•7/25/24, 10:52 PM

downloading models 40 GB

Furkan Gözükara SECourses•7/25/24, 10:53 PM

Furkan Gözükara SECourses•7/25/24, 10:53 PM

but i am pretty sure it will be best

Dazzastrous [4090]•7/25/24, 10:53 PM

what is it?

DDazzastrous [4090]what is it?

Furkan Gözükara SECourses•7/25/24, 10:53 PM

CogVLM image captioning

Furkan Gözükara SECourses•7/25/24, 10:54 PM

https://github.com/THUDM/CogVLM2

GitHub

GitHub - THUDM/CogVLM2: GPT4V-level open-source multi-modal model b...

GPT4V-level open-source multi-modal model based on Llama3-8B - THUDM/CogVLM2

Mattheus Chediak•7/25/24, 11:01 PM

Hey friends! I wan Wondering if someone can help me implement the IDM VTON model to make inference, I tried everything, I'm só frustrated

Mattheus Chediak•7/25/24, 11:02 PM

I'm having a hard time with it

Mattheus Chediak•7/25/24, 11:03 PM

Is it possible to run like without comfyui or gradio

Mattheus Chediak•7/25/24, 11:05 PM

I struggle to find the right checkpoints and reference them to the commands

MMattheus Chediak Hey friends! I wan Wondering if someone can help me implement the IDM VTON model...

Furkan Gözükara SECourses•7/25/24, 11:06 PM

you can use our gradio app source code easiest way

Mattheus Chediak•7/25/24, 11:11 PM

Hey doc, thanks for answering. But can I use as an api even using with gradio? Would it be possible to create an api for it

MMattheus Chediak Hey doc, thanks for answering. But can I use as an api even using with gradio? W...

Furkan Gözükara SECourses•7/25/24, 11:12 PM

gradio gives you api

Furkan Gözükara SECourses•7/25/24, 11:12 PM

but first you need to start gradio app

Mattheus Chediak•7/25/24, 11:13 PM

Oh nice, I'll try that way

Mattheus Chediak•7/25/24, 11:13 PM

I found a step by step implementation too

Mattheus Chediak•7/25/24, 11:14 PM

https://github.com/sangyun884/HR-VITON/issues/45

GitHub

【Not An Issue But Tutorial】A complete tutorial of pre-processing st...

After investigating for 3 days, I got almost all done except for some minor problems. Here is a link of personal made study case of HR-VITON Pre According to explanation from authors: Preprocessing...

Mattheus Chediak•7/25/24, 11:15 PM

But there's a lot of broken stuff

Furkan Gözükara SECourses•7/25/24, 11:15 PM

well our gradio working you can use its code to implement

Mattheus Chediak•7/25/24, 11:28 PM

Nice

Mattheus Chediak•7/25/24, 11:28 PM

I'll let you know after I try

Mattheus Chediak•7/25/24, 11:28 PM

Thank you very much

Mattheus Chediak•7/25/24, 11:29 PM

Furkan Gözükara SECourses•7/25/24, 11:33 PM

you are welcome

Mattheus Chediak•7/25/24, 11:41 PM

it asks me to download this dataset, but its a github repo and nothing inside the folder dataset

Mattheus Chediak•7/25/24, 11:41 PM

didnt find any file called vitonhd_test_tagged there

Mattheus Chediak•7/25/24, 11:48 PM

im downloading from another source, lets see

MMattheus Chediak it asks me to download this dataset, but its a github repo and nothing inside th...

Furkan Gözükara SECourses•7/25/24, 11:52 PM

our vton is here : https://www.patreon.com/posts/86438018

Patreon

1 Click Installer for Automatic1111 SD Web UI, SDXL, ControlNet, Al...

Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon

Mattheus Chediak•7/25/24, 11:58 PM

oh ok, is it paid?

Mattheus Chediak•7/26/24, 12:01 AM

how does it work, if i pay per month, would i be able to learn, download and implement ?

MMattheus Chediak how does it work, if i pay per month, would i be able to learn, download and imp...

Furkan Gözükara SECourses•7/26/24, 12:04 AM

yes

Furkan Gözükara SECourses•7/26/24, 12:04 AM

for 1 month you can download all scripts

Furkan Gözükara SECourses•7/26/24, 12:04 AM

and look their code

Mattheus Chediak•7/26/24, 12:05 AM

oh ok, nice

Gazer•7/26/24, 1:47 AM

@Dr. Furkan Gözükara do you have any resources regarding setting up the different SD tools for a multi-gpu setup? Specifically automatic1111 and Onetrainer

Gazer•7/26/24, 1:47 AM

I saw that you have the same multi-gpu setup as myself actually

Gazer•7/26/24, 1:51 AM

I really just want to be able to train or generate images on either one. Not looking to consolidate resources for a single task

Fabricatedgirls•7/26/24, 2:09 AM

hey dumb question, 4090 comes with a power connector that feeds in 4 power cables from PSU but this PC i'm trying to ram it in only has 3 to feed into it

will it work with 3 or is this a retarded question, asked by an idiot

FFurkan Gözükara SECourses RMBG is best as far as i know

NeoOP•7/26/24, 3:47 AM

I use v1.4 of RMBG, it's very good but sometimes leaves a lot of pixelation in the cropping around the foreground objects and sometimes cuts off hair.

Both of these projects are supposed to improve on that. I've had good success with online demos in comparison.

FFabricatedgirls hey dumb question, 4090 comes with a power connector that feeds in 4 power cable...

J2_Nedo•7/26/24, 5:16 AM

what PSU is that? I doubt it will work

FFabricatedgirls hey dumb question, 4090 comes with a power connector that feeds in 4 power cable...

daroth•7/26/24, 5:28 AM

you don't need 4. 3 is enough. especially if you undervolt the gpu to like 80%