Software Engineering Courses (SECourses)•16mo ago

correct and enter this into your additonal parameters, cause i think the cpu offload checkpointing i

correct and enter this into your additonal parameters, cause i think the cpu offload checkpointing is not working.

--cpu_offlload_checkpointing

MMaxivi correct and enter this into your additonal parameters, cause i think the cpu off...

�

𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮•9/9/24, 1:22 PM

Thanks

MMaxivi correct and enter this into your additonal parameters, cause i think the cpu off...

�

𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮•9/9/24, 1:23 PM

Can I DM you regarding one more thing?

�𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮 Can I DM you regarding one more thing?

MaxiviOP•9/9/24, 1:23 PM

if its feet pics no, other than that then yes

Phuong Bui•9/9/24, 3:54 PM

Is it necessary to train using resolution 1024x1024? For example, my image is a rectangle with a ratio of 768x1024, is it optimal for training or do I have to crop it to a square?

PPhuong Bui Is it necessary to train using resolution 1024x1024? For example, my image is a ...

Dreamer@TDFilmStudio•9/9/24, 4:07 PM

For the Kohya workflow, best results are achieved with the square ratio, which is the standard recommendation, as far as I know.

DDreamer@TDFilmStudio For the Kohya workflow, best results are achieved with the square ratio, which i...

Phuong Bui•9/9/24, 4:12 PM

In the data train, there are many image sources with different resolutions, is that okay? Or should we just get 1 fixed resolution for all train data?

PPhuong Bui In the data train, there are many image sources with different resolutions, is t...

Dreamer@TDFilmStudio•9/9/24, 4:14 PM

You can easily convert various aspect ratios to square size using outpainting. I use 'Expand' function of Adobe Firefly Generative Fill online - fastest and easiest.

PPhuong Bui Is it necessary to train using resolution 1024x1024? For example, my image is a ...

Furkan Gözükara SECourses•9/9/24, 4:22 PM

i suggest you to first train 1024x1024

Furkan Gözükara SECourses•9/9/24, 4:22 PM

once you have some base results

Furkan Gözükara SECourses•9/9/24, 4:22 PM

you can try different aspect ratio multi res and compare

Furkan Gözükara SECourses•9/9/24, 4:22 PM

1024x1024 most safe approach

Furkan Gözükara SECourses•9/9/24, 4:55 PM

it appears that onetrainer has dora for flux

Furkan Gözükara SECourses•9/9/24, 4:55 PM

time to search it :d

FFurkan Gözükara SECourses it appears that onetrainer has dora for flux

Dreamer@TDFilmStudio•9/9/24, 4:58 PM

https://github.com/comfyanonymous/ComfyUI/issues/4695 there have been some issues reported with loading DoRA files trained with OneTrainer in other tools like ComfyUI

GitHub

Load OneTrainer Flux LoRas and DoRas · Issue #4695 · comfyanonymous...

Feature Idea It looks like the Flux branch for OneTrainer is nearing completion - and the results are looking great! However, it seems as though ComfyUI cannot load the resulting .safetensors file....

Zono50•9/9/24, 5:34 PM

if we have 12GB of vram, do we simply run the rank5 or 4 inside of kohya? do we still use flux dev considering that is a much bigger model? @Dr. Furkan Gözükara

DDreamer@TDFilmStudio https://github.com/comfyanonymous/ComfyUI/issues/4695 there have been some is...

Furkan Gözükara SECourses•9/9/24, 5:34 PM

i think he fixed already?

ZZono50 if we have 12GB of vram, do we simply run the rank5 or 4 inside of kohya? do we ...

Furkan Gözükara SECourses•9/9/24, 5:34 PM

you have to use rank 5 or below

Furkan Gözükara SECourses•9/9/24, 5:34 PM

use dev model it auto cast

Furkan Gözükara SECourses•9/9/24, 5:34 PM

make sure you have virtual RAM

Zono50•9/9/24, 5:35 PM

oh ok gotcha, i have 12 GB of vram and 64 GB of system ram, i am watching your video right now and about to start training. I went outside and took some better pictures with the natural lighting outside

Zono50•9/9/24, 5:37 PM

Thank you

FFurkan Gözükara SECourses you have to use rank 5 or below

Dreamer@TDFilmStudio•9/9/24, 6:09 PM

How much is quality loss in the Rank 4 fast version, compared to Rank 3 slow version?

Zono50•9/9/24, 6:37 PM

@Dr. Furkan Gözükara I'm still getting OOM errors when trying to train a lora on 12GB, i'm all the way down to rank 8, i have 11.2 GB of Vram available and still getting it

TheToday•9/9/24, 6:55 PM

Anyone else having trouble with Forge? I'm using the same old thing in Flux and I get OutOfMemory error in Massedcompute with the 48gb

TheToday•9/9/24, 7:06 PM

I think it's when patching Lora, but it worked perfectly a few days ago

Zono50•9/9/24, 7:38 PM

can we use our lora with gguf quantized models of dev?

TheToday•9/9/24, 8:21 PM

the problem is with --always-gpu @Dr. Furkan Gözükara

Zono50•9/9/24, 8:22 PM

what's the recommended way to run inference with low gpu cards? we can't use flux1.dev

Kallamamran•9/9/24, 8:33 PM

Trained a lora with AI-toolkit and the outputs look good, but when I try to run it in Forge it doesn't at all look like the results in Ia-toolkit :/

Kallamamran•9/9/24, 8:33 PM

What am I missing

Kallamamran•9/9/24, 8:34 PM

I have trained on fp16 dev and are usiing dev nf4 in forge. Is that why?

Kallamamran•9/9/24, 8:34 PM

Can't trained LORA's be run in Forge? -

ZZono50 oh ok gotcha, i have 12 GB of vram and 64 GB of system ram, i am watching your v...

Furkan Gözükara SECourses•9/9/24, 8:43 PM

awesome

ZZono50 @Dr. Furkan Gözükara I'm still getting OOM errors when trying to train a lora o...

Furkan Gözükara SECourses•9/9/24, 8:43 PM

which config you using?

ZZono50 can we use our lora with gguf quantized models of dev?

Furkan Gözükara SECourses•9/9/24, 8:44 PM

i havent tried yet

Furkan Gözükara SECourses•9/9/24, 8:44 PM

but swarm ui should work out of box with fp8

KKallamamran I have trained on fp16 dev and are usiing dev nf4 in forge. Is that why?

Furkan Gözükara SECourses•9/9/24, 8:44 PM

nf4 is the problem

ZZono50 what's the recommended way to run inference with low gpu cards? we can't use flu...

Furkan Gözükara SECourses•9/9/24, 8:44 PM

swarmui

Furkan Gözükara SECourses•9/9/24, 8:44 PM

most optimized

rafraf•9/9/24, 8:46 PM

hey @Dr. Furkan Gözükara using swarmui grid generator, if run a grid gen with two params, and you rerun the same params but add an extra value, does it overwrite the entire previous gen? I was under the impression that simply adding a value in an existing param, just inserts the extra gens into the existing grid

Rrafraf hey @Dr. Furkan Gözükara using swarmui grid generator, if run a grid gen with tw...

Furkan Gözükara SECourses•9/9/24, 8:46 PM

i am not sure

Furkan Gözükara SECourses•9/9/24, 8:46 PM

i think it has mixed behaviour

rafraf•9/9/24, 8:47 PM

its really comfusing. using on runpod. ive tested on smalll images to see the mechanism, and it seems sometimes erratic, unpredictable. i am almost sure this the case

rafraf•9/9/24, 8:59 PM

but one thing i d like to know is, if i interrupt the grid genartion, can i re-run it? wi ll it skip already generated images? Or does the interruptioon corrupt the files? Surely you've tested and experienced the behavior?

Rrafraf but one thing i d like to know is, if i interrupt the grid genartion, can i re-r...

Furkan Gözükara SECourses•9/9/24, 9:00 PM

YES

Furkan Gözükara SECourses•9/9/24, 9:00 PM

it can resume

Zono50•9/9/24, 9:00 PM

@Dr. Furkan Gözükara in kohya can we puase and resume traininngs?

ZZono50 @Dr. Furkan Gözükara in kohya can we puase and resume traininngs?

Furkan Gözükara SECourses•9/9/24, 9:03 PM

currently it doesnt work i think

Furkan Gözükara SECourses•9/9/24, 9:03 PM

with fine tuning

Furkan Gözükara SECourses•9/9/24, 9:03 PM

you can use last check point but people said

correct and enter this into your additonal parameters, cause i think the cpu offload checkpointing i

Similar Threads