Software Engineering Courses (SECourses)•11mo ago

Please, I've been here for two days and I can't do anything here anymore... can anyone help

Please, I've been here for two days and I can't do anything here anymore...
can anyone help

Ssergio_gonzo Dr Furkan, for kohya trinaing there is another flux dev model that could be used...

Furkan Gözükara SECourses•2/4/25, 6:49 PM

yes there are

Furkan Gözükara SECourses•2/4/25, 6:49 PM

here my experiments

Furkan Gözükara SECourses•2/4/25, 6:49 PM

https://medium.com/@furkangozukara/thoroughly-experimented-with-fine-tuning-dreambooth-training-of-flux-dev-de-distill-pixelwave-13fab8c625bf

Medium

Thoroughly experimented with Fine-Tuning / DreamBooth training of F...

Thoroughly experimented with Fine-Tuning / DreamBooth training of Flux-dev-de-distill, PixelWave v03, Verus Vision and base FLUX Dev model…

RRockerx If I want to further finetune a lora or a model, what is the best approach ? Do ...

Furkan Gözükara SECourses•2/4/25, 6:49 PM

i rather prefer each time train from scratch with improved dataset

�𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮 @Dr. Furkan Gözükara Is it possible to train a style and an object in the same L...

Furkan Gözükara SECourses•2/4/25, 7:02 PM

if they are different class yes can work

Furkan Gözükara SECourses•2/4/25, 7:02 PM

i trained a person and a handbag

Rrob What are the fundamental differences between kohya, onetrainer and simpletuner? ...

Furkan Gözükara SECourses•2/4/25, 7:03 PM

they use different scripts

Furkan Gözükara SECourses•2/4/25, 7:03 PM

but if implementation is same should perform same

AAiInfluence Click to see attachment

Furkan Gözükara SECourses•2/4/25, 7:03 PM

nice

AiInfluence•2/4/25, 7:04 PM

@Furkan Gözükara SECourses SOS

I need a list of available stable diffusion classes

AiInfluence•2/4/25, 7:04 PM

Does it work with the T5Xxl?

AAiInfluence @Furkan Gözükara SECourses SOS 🚨 I need a list of available stable diffusion cl...

Furkan Gözükara SECourses•2/4/25, 7:04 PM

i test manually there is no such thing

Furkan Gözükara SECourses•2/4/25, 7:05 PM

test your prompt and see if generates similar thing

AiInfluence•2/4/25, 7:05 PM

That's a good approach yeah

RRockerx @Dr. Furkan Gözükara can you suggest ? If I want to further finetune a lora or a...

Furkan Gözükara SECourses•2/4/25, 7:05 PM

improve dataset and train from 0 again - best way

AiInfluence•2/4/25, 7:06 PM

@Furkan Gözükara SECourses I saw your new upscale gradio , does it reach supir quality?

Mmmercuri @Dr. Furkan Gözükara What's your recommendation for training with a minimum numb...

Furkan Gözükara SECourses•2/4/25, 7:06 PM

you can data augment and train - crop differently - i trained with like 3 or 4 images person worked fairly good

AAiInfluence @Furkan Gözükara SECourses I saw your new upscale gradio , does it reach supir q...

Furkan Gözükara SECourses•2/4/25, 7:06 PM

nope

Wwardensc2 @Dr. Furkan Gözükara the newest of your ComfyUI install include DeepSpeed, does ...

Furkan Gözükara SECourses•2/4/25, 7:06 PM

only if the model uses

Furkan Gözükara SECourses•2/4/25, 7:06 PM

mostly llms vlms

..tarkan @Dr. Furkan Gözükara Here a gen from a custom fine tune on large images I’ve til...

Furkan Gözükara SECourses•2/4/25, 7:07 PM

nice

Jjulius made a new flux fine tuning model of my friend with 58 images, also gave great a...

Furkan Gözükara SECourses•2/4/25, 7:08 PM

yes i also find more better than fewer

..tarkan Click to see attachment

Furkan Gözükara SECourses•2/4/25, 7:09 PM

excellent

NNeuromasters Wow, there are so many neural nets that you've taken apart and assembled

Furkan Gözükara SECourses•2/4/25, 7:09 PM

100% here so far

Furkan Gözükara SECourses•2/4/25, 7:09 PM

Furkan Gözükara SECourses•2/4/25, 7:10 PM

i tested all the apps and fixed broken ones due to new libraries

DDarth Teethius Has anyone used the nee deep face similarity app? It works great but I'm not sur...

Furkan Gözükara SECourses•2/4/25, 7:10 PM

it is comparative so good to see ranked. but for values hard to tell

VVegan Apps Where are the models saved that are downloaded the first time I run the video ge...

Furkan Gözükara SECourses•2/4/25, 7:11 PM

if not in same folder than it means it is in the hugging face cache

Furkan Gözükara SECourses•2/4/25, 7:11 PM

so yes it is hugging face cache

Furkan Gözükara SECourses•2/4/25, 7:12 PM

MMeLL Please, I've been here for two days and I can't do anything here anymore... can...

Furkan Gözükara SECourses•2/4/25, 7:12 PM

are you running as administrator?

Furkan Gözükara SECourses•2/4/25, 7:12 PM

dont do that ever

Furkan Gözükara SECourses•2/4/25, 7:13 PM

unless i written in the patreon post

Furkan Gözükara SECourses•2/4/25, 7:13 PM

because you see it shows windows

Furkan Gözükara SECourses•2/4/25, 7:13 PM

vp•2/4/25, 7:42 PM

doc - possible for you to upload deepspeed whl and triton whl for python 311 into your huggingface mmorpg repo

vp•2/4/25, 7:45 PM

solved, disregard

AiInfluence•2/4/25, 9:34 PM

@Furkan Gözükara SECourses SOS

https://www.instagram.com/p/DFqmMs_IKyW/?img_index=1&igsh=dmJrbmhxaGdwZG91

acknowledge.ai

Bytedance, TikTok’s parent company, has introduced OmniHuman-1, a groundbreaking AI model that generates highly realistic human videos from just a single image and audio.

Capable of adapting to any aspect ratio and body proportion, OmniHuman-1 pushes the boundaries of AI-generated content.

This innovation could revolutionize digital media, e...

Likes

107