Software Engineering Courses (SECourses)•17mo ago

I wanted to try this: https://civitai.com/models/705681?modelVersionId=789392

GGUF: HyperFlux 16-Steps (Flux.1 Dev + ByteDance HyperSD LoRA) - Q8...

Warning: This is the 16-step model. The faster 8-step model can be found HERE [Note: Unzip the download to get the GGUF. Civit doesn't support it n...

Uumuthasanoglu Hey guys, how can I use .gguf format models in SwarmUI?

Furkan Gözükara SECourses•8/31/24, 5:04 PM

i am gonna ask this now

umuthasanogluOP•8/31/24, 5:05 PM

I just figured it out. For those who want to try out: In order to work, you need to manually edit metadata of the model and select architecture type. All gguf models goes into unet folder and after restart it automatically downloads Comfy GGUF Workflow.

Uumuthasanoglu I wanted to try this: https://civitai.com/models/705681?modelVersionId=789392

umuthasanogluOP•8/31/24, 5:06 PM

I'm testing this right now but so far it looks great for 12-16 gb VRAM GPU's.

druhl•8/31/24, 5:19 PM

Is there like a ComfyUI XY Plot workflow to test/ compare multiple Flux Lora models?

Ddruhl Is there like a ComfyUI XY Plot workflow to test/ compare multiple Flux Lora mod...

Furkan Gözükara SECourses•8/31/24, 5:20 PM

why not use swarm?

FFurkan Gözükara SECourses why not use swarm?

druhl•8/31/24, 5:21 PM

Would it mean relearning a lot of stuff?

Ddruhl Would it mean relearning a lot of stuff?

Furkan Gözükara SECourses•8/31/24, 5:21 PM

nope

Furkan Gözükara SECourses•8/31/24, 5:21 PM

i shown how to make

Furkan Gözükara SECourses•8/31/24, 5:22 PM

https://youtu.be/nySGu12Y05k

YouTubeSECourses

FLUX LoRA Training Simplified: From Zero to Hero with Kohya SS GUI ...

Ultimate Kohya GUI FLUX LoRA training tutorial. This tutorial is product of non-stop 9 days research and training. I have trained over 73 FLUX LoRA models and analyzed all to prepare this tutorial video. The research still going on and hopefully the results will be significantly improved and latest configs and findings will be shared. Please wat...

Furkan Gözükara SECourses•8/31/24, 5:22 PM

52:55 Grid Generator tool for selecting LoRAs and prompts
53:59 Generating the grid and expected results
56:57 Analyzing grid results in Swarm UI

Furkan Gözükara SECourses•8/31/24, 5:22 PM

way easier than comfyui

Furkan Gözükara SECourses•8/31/24, 5:22 PM

and uses comfyui at back end

druhl•8/31/24, 5:23 PM

Yea, I saw the video. Need to setup swarm first, then get it up and running

LW24Ai•8/31/24, 5:55 PM

Help me to understand this error

LW24Ai•8/31/24, 5:56 PM

I'm using the flux1CompactCLIPAnd_Flux1DevFp8 training model

LW24Ai•8/31/24, 5:59 PM

This model doesn't fit?

FFurkan Gözükara SECourses https://youtu.be/nySGu12Y05k

Kenzo•8/31/24, 6:06 PM

is it possible to do everything like you on this video but on Runpod ?

LLW24Ai Help me to understand this error 🥹

Furkan Gözükara SECourses•8/31/24, 6:07 PM

dont use flux1CompactCLIPAnd_Flux1DevFp8

Furkan Gözükara SECourses•8/31/24, 6:08 PM

use fp16 base model

KKenzo is it possible to do everything like you on this video but on Runpod ?

Furkan Gözükara SECourses•8/31/24, 6:08 PM

yes. i also made a video for runpod

Furkan Gözükara SECourses•8/31/24, 6:08 PM

still editing it

FFurkan Gözükara SECourses dont use flux1CompactCLIPAnd_Flux1DevFp8

LW24Ai•8/31/24, 6:10 PM

The base model will definitely work on my Nvidea RTX 3060 12gb Ram 32gb video card? Because I can't on the base model to do generation, not enough memory for generation

LLW24Ai The base model will definitely work on my Nvidea RTX 3060 12gb Ram 32gb video ca...

Furkan Gözükara SECourses•8/31/24, 6:11 PM

yes

Furkan Gözükara SECourses•8/31/24, 6:11 PM

during training doesnt matter

Furkan Gözükara SECourses•8/31/24, 6:11 PM

it will be auto casted

FFurkan Gözükara SECourses yes. i also made a video for runpod

STUFCS•8/31/24, 6:14 PM

do you know when will it be available ?

SSTUFCS do you know when will it be available ?

Furkan Gözükara SECourses•8/31/24, 6:15 PM

i am editing hopefully tomorrow

STUFCS•8/31/24, 6:17 PM

SUPER !

dxqb•8/31/24, 7:37 PM

dxqb•8/31/24, 7:41 PM

FFurkan Gözükara SECourses it is 1.25$ per hour with our coupon

GomezBro•8/31/24, 9:13 PM

Link to site, coupon and the multi GPU video when you drop it. I will do this immedietely

GomezBro•8/31/24, 9:37 PM

What do you estimate time/cost would be for 1000 images?

macba•8/31/24, 9:50 PM

@Dr. Furkan Gözükara and colleagues, have you seen this?

https://github.com/bghira/SimpleTuner

GitHub

GitHub - bghira/SimpleTuner: A general fine-tuning kit geared towar...

A general fine-tuning kit geared toward diffusion models. - bghira/SimpleTuner

FFurkan Gözükara SECourses yes

LW24Ai•8/31/24, 9:53 PM

You tricked me. The 23gb FLUX dev FP16 with preset Rank_5_11498MB_Slow does not fit my 12gb configuration. As before this model is not suitable for training and gening

AIGambino•8/31/24, 10:12 PM

Dr When I click windows install step 1 it just opens and closes

AIGambino•8/31/24, 10:13 PM

All my other python applications work fine except this one for some reason I use the correct python install 64bit

AIGambino•8/31/24, 10:24 PM

LLW24Ai You tricked me. The 23gb FLUX dev FP16 with preset Rank_5_11498MB_Slow does not ...

Evivrus•8/31/24, 10:24 PM

Are you running your OS with the same 12GB card?

AAIGambino Dr When I click windows install step 1 it just opens and closes

Evivrus•8/31/24, 10:27 PM

Which 1 step installer?

AIGambino•8/31/24, 10:30 PM

In the kohya 1 click installer on his patreon

EEvivrus Are you running your OS with the same 12GB card?

LW24Ai•8/31/24, 10:31 PM

Yes and RAM 32GB

LW24Ai•8/31/24, 10:34 PM

I used all Config file train_data_dir. 8 GB GPUs : Rank_9_7514MB.json, 10 GB GPUs : Rank_7_9502MB.json, 12 GB GPUs : Rank_5_11498MB_Slow.json, all give memory errors

pixelscience•8/31/24, 10:55 PM

I do this all the time on accident, but make sure you are using the LORA tab and not the Dreambooth tab in Koyha. It will fail with out of memory errors.

LLW24Ai I used all Config file train_data_dir. 8 GB GPUs : Rank_9_7514MB.json, 10 GB GPU...

Evivrus•8/31/24, 10:59 PM

Hmm, I can see the 12gb it looks like it is failing pretty early. Do you have a game running in the BG or another stable diffusion UI running in the BG.

It looks like it is failing because there is only 5gb free on the card and it needs 6gb

EEvivrus Hmm, I can see the 12gb it looks like it is failing pretty early. Do you have a ...

LW24Ai•8/31/24, 11:06 PM

No, I don't have any other background tasks, I only work with Kohya.

LW24Ai•8/31/24, 11:10 PM