so 2 concepts for the images (1024x1024 and 896x1152). i have 50 images each. since it's 2 concepts
so 2 concepts for the images (1024x1024 and 896x1152). i have 50 images each. since it's 2 concepts do i use 50 or 100?
Flogic simple
Fat 1 epoch you have 100 train images
Fthen you should use 100 reg images
F50 from each in that case
Jdue to block swap and vae_cache_cpu enabled.
interestingly enough it made no difference in my case for speed whether i turn it on or not for that 480z360 dataset , tested speeds with and without. (without it fits in dedicated vram without shared mem as well)
(though usualy vram bottleneck does limit speeds in other instances)
interestingly enough it made no difference in my case for speed whether i turn it on or not for that 480z360 dataset , tested speeds with and without. (without it fits in dedicated vram without shared mem as well)
(though usualy vram bottleneck does limit speeds in other instances)
Ji am still messing around with what barely fits in vram, apparently as long as there is about 1gb vram dedicated available it will run full speed (400 watt at 70% power limit)
JFor Wan2.1 T2V using (25 videos) 480x360@61 and (23) images 960x720 fits just perfectly in an RTX 5090. Wondering about the results, but this is the most I was sable to cram into the VRAM without going overboard and not using any offloading / shared vram
J
CYesterday, I extracted a LORA from my Dreambooth model (of my character) that I trained in Kohya GUI on the FLUX.dev model. I wanted to see how the LORA would perform with the Flux Krea model, but unfortunately, it doesn't look great.
I guess I'll have to train a new LORA specifically on the Flux Krea model, or train an entire Dreambooth model from scratch.
I guess I'll have to train a new LORA specifically on the Flux Krea model, or train an entire Dreambooth model from scratch.
JMakes sense I guess
AI can confirm. Lora trained on Dev inferenced on krea is not that good
ABut a checkpoint with krea Lora works
CI'm currently training a test LORA on the wan22 low noise model, specifically a LORA for a person or character. From what I understand, it's best to train it on a low noise model. It's a fast training, only 30 images in diffusion pipe wsl. It should take about 1.5 hours.
Almk how it went
AI tried wan 2.2 t2i and I was very disappointed
Atext was all wrong and textures / quality same as krea
CI will
Ais this musubi
CDiffusion-Pipe - best for me. using many times and created many nice Loras for wan2.1
Fi think kohya lora extraction is not working accurate
Janyone know how to upload finetuned flux dev model ( dreambooth style ) to replicate so i can call it with a api?
F
Fwe had requested base model support i am not sure if he added
Dcan i run multiple instances of onetrainer(gui) or at least cmd? because i don't seem to find any batch processing in the interface
Dlike if i wanted to train the same dataset with the same settings but different base models (for a lora) it would be nice if it would do them after another over night. right now i run it, wait around 1-2hours and then start a new one
Fyou cant queue
Fdo you have multiple gpus?
Dif we count the 4090 in the cupboard, ready to sell, yes. no, just the 5090 in a pc. i was hoping it would be like with gradio stuff
Dso IF i could open it two times, it would do it at the same time and fk things up because of that? or would one of the instances just say nope
Fyou can open 2 instance
Fand set different cuda device as well
Fbut if you have single gpu i dont see benefit
Fif you do that change folders on each one to different
Fso wont conflict
Dah ok. my thought would be since once instance runs like 1-2 hours , that i could let it do 4-5 trainings over night
Dbecause when i sleep i and one is done, i cant start the next one with a different checkpoint
Fi dont know if queue
Fyou can try
Jkoyha or musubi may perhaps let you train from the command line (batch)
J@Dr. Furkan Gözükara Perhaps interesting for you, trying out now for Wan22
https://civitai.com/articles/17740
https://civitai.com/articles/17740
The basis for this workflow is my original WAN2.1 training guide: My WAN2.1 LoRa training workflow TLDR | Civitai In this new article I will explai...
JSeems like it is using a seperate branch of musubi for wan22 training
Fye musubi will be also my choice
Fi will make my own gradio interface easier one
JAweomse. By the way, pro tip, I got a "flash_attn2" error running it on my RTX 5090 , however when I use the command line like this, loading CL before the loading the venv, it works just fine:
C:
cd "C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\Build"
vcvarsall.bat x86_amd64
cl
C:\musubi-tuner
cd venv
cd scripts
activate
cd ..
cd ..
Ahi jonko
JI am sure the batch commands can be done less sloppy but the point is that CL needs to be loaded apparently