Software Engineering Courses (SECourses)•17mo ago

i mean diffusers : https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flu

i mean diffusers : https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md

GitHub

diffusers/examples/dreambooth/README_flux.md at main · huggingface/...

Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX. - huggingface/diffusers

DDazzastrous [4090]what is the difference between comfui installer v3 and v4?

Furkan Gözükara SECoursesOP•8/11/24, 10:47 PM

i dont remember check info

Dazzastrous [4090]•8/11/24, 10:47 PM

lol

FFurkan Gözükara SECourses i dont remember check info 😄

AIGambino•8/11/24, 10:47 PM

is there a downside to simple tuner?

AAIGambino is there a downside to simple tuner?

Furkan Gözükara SECoursesOP•8/11/24, 10:57 PM

harder to use. i dont know if working accurate never tested.

FFurkan Gözükara SECourses Click to see attachment

VAMP•8/12/24, 12:50 AM

Shouldn't that be expected?

FFurkan Gözükara SECourses lol look at vram

VAMP•8/12/24, 12:50 AM

When even 24gb dedicated ram becomes less

FFurkan Gözükara SECourses i am waiting next gen gpus to move to 128 gb faster RAM

VAMP•8/12/24, 1:12 AM

Doc we need to do a GPU heist at the Nvidia headquarters

VVAMP Doc we need to do a GPU heist at the Nvidia headquarters 🤣 .

Furkan Gözükara SECoursesOP•8/12/24, 1:36 AM

we need

FFurkan Gözükara SECourses Click to see attachment

Neo•8/12/24, 1:50 AM

Thank you so much for this, you've optimised one of my processes around image processing so much with this!!!!

FFurkan Gözükara SECourses i am waiting next gen gpus to move to 128 gb faster RAM

Neo•8/12/24, 1:52 AM

I don't think 5090 will have that much VRAM, 48GB at max, I dont even think nvidia will go that route. Truly cloud computing for this stuff is the future-- and I am saying this as a 3090 and 4090 owner

NNeo I don't think 5090 will have that much VRAM, 48GB at max, I dont even think nvid...

Furkan Gözükara SECoursesOP•8/12/24, 2:31 AM

48 gb would be amazing

Furkan Gözükara SECoursesOP•8/12/24, 2:31 AM

rumos are like 28 32 which are totally lame shameless

NNeo Thank you so much for this, you've optimised one of my processes around image pr...

Furkan Gözükara SECoursesOP•8/12/24, 2:31 AM

you are welcome. this is the best atm

FFurkan Gözükara SECourses Click to see attachment

Neo•8/12/24, 2:59 AM

These examples are extremely good (at work so can't test). Was this using the general model or the human specialised model? https://huggingface.co/datasets/schirrmacher/humans

schirrmacher/humans · Datasets at Hugging Face

Bill Meeks•8/12/24, 4:56 AM

I'm making a lot of grids for Very Special characters, so I built a quick web app to speed up evaluating them! I hope you find this free tool useful. https://everlyheights.tv/tools/stable-diffusion-tools/everly-heights-xyz-grid-evaluator/

Everly Heights | Stories set in the fictional town of Everly Heights, OhioEverly Heights

Everly Heights XYZ Grid Evaluator | Everly Heights | Stories set in...

The Everly Heights XYZ Grid Evaluator is a powerful web-based tool designed to help you evaluate and rank outputs from your Stable Diffusion AI image models after you generate an XYZ Plot/Grid to test various settings, including LoRAs (Low-Rank Adaptation) and more technical settings like Steps and CFG. Whether you're an AI researcher, developer...

FFurkan Gözükara SECourses Click to see attachment

Kallamamran•8/12/24, 7:56 AM

Needed in ComfyUI

Kallamamran•8/12/24, 7:57 AM

All these stand-alone "apps" are cool and all, but it's not really useful jumping between all the different apps

Upscaling is fine though sice that's usually a last stage

fekdaoui•8/12/24, 7:59 AM

hi all, do we have any comfyui workflow to train flux on a character (like using dreambooth)

Kallamamran•8/12/24, 8:08 AM

No. Not yet. Demands to much VRAM so noone has put any effort into that

Kallamamran•8/12/24, 8:09 AM

Flux trainings is done on rental-GPU's for now

fekdaoui•8/12/24, 8:17 AM

okay i see, too bad!

fekdaoui•8/12/24, 10:49 AM

PS: you can run any comfyui workflow on rented GPUs on replicate: https://replicate.com/fofr/any-comfyui-workflow

fofr/any-comfyui-workflow – Replicate

Run any ComfyUI workflow. Guide: https://github.com/fofr/cog-comfyui

Mattheus Chediak•8/12/24, 11:02 AM

hey doc, any toughts on how can i make the supir and vton app serverless after i deployed into runpod ?

Ffekdaoui PS: you can run any comfyui workflow on rented GPUs on replicate: https://replic...

Haashim•8/12/24, 4:32 PM

interesting.. can you run lora models as well?

Fever308•8/12/24, 4:40 PM

Is there a way to save your state from Massed Compute? It's kind of annoying that I have to reinstall all the custom nodes and models I wanna use everytime I boot an instance. Runpod's nice that I can keep a storage instance for cheap/hr

icchansan•8/12/24, 5:55 PM

Hi guys, there's any tuto for loras on flux?

Shinnok•8/12/24, 8:14 PM

guys i tried to use topaz but a toaster runs better than my pc .. is there any colab or free alternative to topaz video enchancer???

icchansan•8/12/24, 8:21 PM

how long its the video?

Shinnok•8/12/24, 8:24 PM

5 seconds

icchansan•8/12/24, 8:50 PM

hmm then something its odd

AIGambino•8/13/24, 2:17 AM

is there a one click installer for ai toolkit?

Ffekdaoui hi all, do we have any comfyui workflow to train flux on a character (like using...

Furkan Gözükara SECoursesOP•8/13/24, 7:14 AM

i plan kohya tutorial soon for flux training

MMattheus Chediak hey doc, any toughts on how can i make the supir and vton app serverless after i...

Furkan Gözükara SECoursesOP•8/13/24, 7:14 AM

no idea you need some programming skills

FFever308 Is there a way to save your state from Massed Compute? It's kind of annoying tha...

Furkan Gözükara SECoursesOP•8/13/24, 7:15 AM

sadly not

Furkan Gözükara SECoursesOP•8/13/24, 7:15 AM

best is upload into hugging face

Furkan Gözükara SECoursesOP•8/13/24, 7:15 AM

which i do

Iicchansan Hi guys, there's any tuto for loras on flux?

Furkan Gözükara SECoursesOP•8/13/24, 7:15 AM

hopefully soon

SShinnok guys i tried to use topaz but a toaster runs better than my pc .. is there any c...

Furkan Gözükara SECoursesOP•8/13/24, 7:17 AM

there is this app but only on windows i presume

Furkan Gözükara SECoursesOP•8/13/24, 7:17 AM

https://github.com/AaronFeng753/Waifu2x-Extension-GUI

GitHub

GitHub - AaronFeng753/Waifu2x-Extension-GUI: Video, Image and GIF u...

Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, Real-CUGAN, RTX Video Super Resolution VSR, SRMD, RealSR, Anime4K, RIFE, I...

Kallamamran•8/13/24, 8:44 AM

Anyone else having problems running the NF4 model in ComfyUI?

Kallamamran•8/13/24, 8:44 AM

I'm fully updated

Kallamamran•8/13/24, 10:19 AM

Runs in Forge though

Kallamamran•8/13/24, 10:58 AM

Trying to wrap my head around the differences between the weight types, models and VAE's.
I find that using the 327kb .sft file or using the 163kb .safetensor file produces results that are the same
Using weight type default produces way better images, but it takes longer. VAE-Decode takes tie with default. With the other ones it just takes a second