Software Engineering Courses (SECourses)•6mo ago

Hey I'm new around here and have very little coding knowledge, but I'm getting these error messages

Hey I'm new around here and have very little coding knowledge, but I'm getting these error messages when installing ultimate image processing V15 on massedcompute. Would appreciate any help

Thanks

FFurkan Gözükara SECourses https://www.patreon.com/posts/120352012

Shyam Nimmana•7/2/25, 5:10 PM

I followed this post. I got YOLO/SAM2 Detected Images, but I don't get the cropped images..

Shyam Nimmana•7/2/25, 6:54 PM

I got this image, but not the cropped one.

Gg7ants80 Hey I'm new around here and have very little coding knowledge, but I'm getting t...

Furkan Gözükara SECourses•7/2/25, 9:18 PM

first one not error

Furkan Gözükara SECourses•7/2/25, 9:18 PM

but second one is

Furkan Gözükara SECourses•7/2/25, 9:18 PM

let me test

Furkan Gözükara SECourses•7/2/25, 9:19 PM

you selected this right @g7ants80

SShyam Nimmana I got this image, but not the cropped one.

Furkan Gözükara SECourses•7/2/25, 9:19 PM

it doesnt crop

Furkan Gözükara SECourses•7/2/25, 9:19 PM

what you need exactly?

Furkan Gözükara SECourses•7/2/25, 9:19 PM

i mean it crops to aspect ratio not the target

Furkan Gözükara SECourses•7/2/25, 9:20 PM

if you tell me what you need i may code it

Gg7ants80 Hey I'm new around here and have very little coding knowledge, but I'm getting t...

Furkan Gözükara SECourses•7/2/25, 9:53 PM

hello sorry for this error fixed with v17

Furkan Gözükara SECourses•7/2/25, 9:53 PM

https://www.patreon.com/posts/120352012

Patreon

Ultimate Image Processing APP : Batch Cropping, Zooming In, Resizin...

Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon

FFurkan Gözükara SECourses if you tell me what you need i may code it

Shyam Nimmana•7/3/25, 3:31 AM

It's working now, I am using version 11, and it works with version 11. sir! We can do it easily with other software like birme.org, xnConvert or other online tools.

Nisar•7/3/25, 5:22 AM

@Furkan Gözükara SECourses are you online now ?

SShyam Nimmana It's working now, I am using version 11, and it works with version 11. sir! We c...

Furkan Gözükara SECourses•7/3/25, 9:57 AM

great

NNisar <@205854764540362752> are you online now ?

Furkan Gözükara SECourses•7/3/25, 9:57 AM

yes

FFurkan Gözükara SECourses hello sorry for this error fixed with v17

g7ants80OP•7/4/25, 2:13 AM

Thank you! I'll see if it works now

g7ants80OP•7/4/25, 3:41 AM

Getting this now when I start training

Screenshot_2025-07-03_at_11.40.00_PM.png

ghstoic•7/4/25, 11:55 AM

Anyone have any idea what GPU on MssedCompute is the closest equivalent to RTX 5090's 3s/it for finetuning? (single only, not duals). Feel the need for speed :p

Gg7ants80 Getting this now when I start training

Furkan Gözükara SECourses•7/4/25, 11:57 AM

it tells you the error

Furkan Gözükara SECourses•7/4/25, 11:57 AM

did you set your training images folder?

Gghstoic Anyone have any idea what GPU on MssedCompute is the closest equivalent to RTX 5...

Furkan Gözükara SECourses•7/4/25, 11:57 AM

h100 faster

Furkan Gözükara SECourses•7/4/25, 11:57 AM

a100 can be close

ghstoic•7/4/25, 11:58 AM

Thanks Doc

diegoarmanda•7/4/25, 12:20 PM

I am currently following and running the training from: https://www.patreon.com/posts/kohya-flux-fine-112099700
Once the training is finished, can the output file be used as a LoRA data file in ComfyUI using the Flux model?

Sorry if my question is confusing, as I am still a beginner.
Thank you!

Patreon

Kohya FLUX Fine Tuning (Full Checkpoints) Training Full Tutorial Fo...

Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon

FFurkan Gözükara SECourses i recommend after that extract lora

diegoarmanda•7/4/25, 2:35 PM

I am a beginner and would like to ask:
If I train a model using FLUX Full Fine-Tuning or DreamBooth, can the resulting trained file be used as a LoRA model in a ComfyUI workflow?

Sorry if my question is basic, I am still learning. Thank you!

javajunkie•7/4/25, 5:48 PM

Hi, thanks for your excellent tutorials and articles.

I'm having an issue with runpods and LoRA. I completed some tests locally and know have started over with runpods. When I start trainingstart training I get an error you've been asked about before; LoRA type must be set to 'Flux1', 'Flux1 OFT' or 'LyCORIS' if Flux1 checkbox is checked.LoRA type must be set to 'Flux1', 'Flux1 OFT' or 'LyCORIS' if Flux1 checkbox is checked. You've said to another user that they've set the model path incorrect, well my model is in the /workspace/ folder and my path is set as such. I've removed the model and downloaded it fresh, but the error persists, sadly.

~~Am I missing something else?~~

Disregard, loading different base configs seemed to fix it.

Ddiegoarmanda I am a beginner and would like to ask: If I train a model using FLUX Full Fine-T...

Furkan Gözükara SECourses•7/4/25, 11:06 PM

yes

Furkan Gözükara SECourses•7/4/25, 11:06 PM

100%

Jjavajunkie Hi, thanks for your excellent tutorials and articles. ~~I'm having an issue wit...

Furkan Gözükara SECourses•7/4/25, 11:06 PM

great

Badnerle | Can•7/5/25, 12:28 AM

for what reason do we extract lora after dreambooth?

diegoarmanda•7/5/25, 4:31 AM

Hello, I’m still a beginner and learning through SECourses, so I apologize if my question is unclear.

I successfully trained a character using Flux Full Fine Tuning (or DreamBooth), and I tested the result in ComfyUI as a UNet model (without using flux1.Dev). The results were very realistic and successful.

Now I’m wondering:

Can this trained model be used as a replacement for Flux Kontent?

Or, can I use Flux Kontent and combine it with my trained model as a LoRA?

Thank you for your help!

BBadnerle | Can for what reason do we extract lora after dreambooth?

Furkan Gözükara SECourses•7/5/25, 11:52 AM

if you need lora

Furkan Gözükara SECourses•7/5/25, 11:52 AM

otherwise you dont need and i dont recommned dreambooth works better

Ddiegoarmanda Hello, I’m still a beginner and learning through SECourses, so I apologize if my...

Furkan Gözükara SECourses•7/5/25, 11:52 AM

1 : nope different model

Furkan Gözükara SECourses•7/5/25, 11:52 AM

2 : nope sadly

Furkan Gözükara SECourses•7/5/25, 11:53 AM

but i didnt test lora on kontext yet so cant say for 100%

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•7/6/25, 1:04 PM

I want to fine tune on a specific quality type of images of women. Not 1 character, but I want the fine tune to be able to generate woman with same quality as training data. Say I have pics of 5 to 10 different women of multiple shapes, hair, body, ethnicity etc. How many pics would be needed for a high quality finetune? Ideally it should be able to generate women not in the training set, I.e. an Arab woman, but with same quality as training pics. Unsure how to proceed, only done fine tune with 1 character so far. I guess captions should be needed here.

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭I want to fine tune on a specific quality type of images of women. Not 1 charact...

Furkan Gözükara SECourses•7/6/25, 10:56 PM

you may try bigger fine tunes people published with good prompting

Furkan Gözükara SECourses•7/6/25, 10:56 PM

otherwise you are looking for rather general fine tune

Furkan Gözükara SECourses•7/6/25, 10:57 PM

so you need more images the better and use good captions

Henry•7/7/25, 7:20 PM

Hello! I am trying to get the kaggle notebook to run "kohya-sdxl-lora-training-on-a-free-kaggle-notebook_v28", but the moment I import it just starts downloading a ton of dependencies automatically. I did not see this in the tutorial. What is the expected behavior? Thanks in advance

Henry•7/7/25, 7:24 PM

Also, I can seem to edit the GPUs or the folder directories to point to training images

FFurkan Gözükara SECourses yes ai video upscaler is my priority

Cryptozow.x•7/7/25, 9:46 PM

Hey, just wanted to throw this here FYI in case you're looking for STAR alternatives within your APP, you can check if you want, they claim to be better than STAR, however, I haven't been able to test it out.
https://github.com/yjsunnn/DLoRAL?tab=readme-ov-file

GitHub

GitHub - yjsunnn/DLoRAL: Official Implementation of “One-Step Dif...

Official Implementation of “One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution” - yjsunnn/DLoRAL