Software Engineering Courses (SECourses)•5mo ago

like if i wanted to train the same dataset with the same settings but different base models (for a l

like 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

Ddschulie like if i wanted to train the same dataset with the same settings but different ...

Furkan Gözükara SECourses•8/5/25, 8:32 PM

you cant queue

Furkan Gözükara SECourses•8/5/25, 8:32 PM

do you have multiple gpus?

dschulieOP•8/5/25, 8:33 PM

if 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

dschulieOP•8/5/25, 8:34 PM

so 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

Ddschulie so IF i could open it two times, it would do it at the same time and fk things u...

Furkan Gözükara SECourses•8/5/25, 8:39 PM

you can open 2 instance

Furkan Gözükara SECourses•8/5/25, 8:39 PM

and set different cuda device as well

Furkan Gözükara SECourses•8/5/25, 8:39 PM

but if you have single gpu i dont see benefit

Furkan Gözükara SECourses•8/5/25, 8:40 PM

if you do that change folders on each one to different

Furkan Gözükara SECourses•8/5/25, 8:40 PM

so wont conflict

dschulieOP•8/5/25, 8:40 PM

ah ok. my thought would be since once instance runs like 1-2 hours , that i could let it do 4-5 trainings over night

dschulieOP•8/5/25, 8:41 PM

because when i sleep i and one is done, i cant start the next one with a different checkpoint

Ddschulie ah ok. my thought would be since once instance runs like 1-2 hours , that i coul...

Furkan Gözükara SECourses•8/5/25, 8:46 PM

i dont know if queue

Furkan Gözükara SECourses•8/5/25, 8:46 PM

you can try

Ddschulie can i run multiple instances of onetrainer(gui) or at least cmd? because i don't...

JonkoXL•8/5/25, 11:41 PM

koyha or musubi may perhaps let you train from the command line (batch)

JonkoXL•8/6/25, 12:39 PM

@Dr. Furkan Gözükara Perhaps interesting for you, trying out now for Wan22
https://civitai.com/articles/17740

My WAN2.2 LoRa training workflow TLDR | Civitai

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...

JonkoXL•8/6/25, 12:39 PM

Seems like it is using a seperate branch of musubi for wan22 training

JJonkoXL Seems like it is using a seperate branch of musubi for wan22 training

Furkan Gözükara SECourses•8/6/25, 1:25 PM

ye musubi will be also my choice

Furkan Gözükara SECourses•8/6/25, 1:25 PM

i will make my own gradio interface easier one

JonkoXL•8/6/25, 1:27 PM

Aweomse. 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 ..

AiInfluence•8/6/25, 1:28 PM

hi jonko

JonkoXL•8/6/25, 1:28 PM

I am sure the batch commands can be done less sloppy but the point is that CL needs to be loaded apparently

AiInfluence•8/6/25, 1:28 PM

can you pls share results and your opinion when you finish wan 2.2 training? thanks

skyrrr•8/7/25, 11:55 AM

Hey does anyone tried a full finetune with Flux Krea ? Any samples to share/insights ? Curious

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•8/7/25, 2:00 PM

What is the best finetune checkpoint for consistent character to avoid plastic flux look? Is krea or wan or qwan better than flux dev? I was optimistic about krea, was it not as good after all?

Ella•8/7/25, 5:18 PM

Anyone know How to copy and paste in massed compute?

EElla Anyone know How to copy and paste in massed compute?

cyberbol•8/7/25, 7:37 PM

use mouse copy and paste, not CTRL+C etc... sometimes not work at forst times.

cyberbol•8/7/25, 7:48 PM

Training wan2.2 High-Noise in musubi-tuner in progress.

Next Low-Noise and i will see result of my first wan2.2 lora.

Ccyberbol use mouse copy and paste, not CTRL+C etc... sometimes not work at forst times.

Ella•8/7/25, 10:13 PM

thank you

Ccyberbol Training wan2.2 High-Noise in musubi-tuner in progress. Next Low-Noise and i ...

JonkoXL•8/8/25, 2:01 PM

t2v or i2v?

JonkoXL•8/8/25, 2:01 PM

t2v works for me

JJonkoXL t2v or i2v?

cyberbol•8/8/25, 2:26 PM

@Ella t2v. But I used just 30 photos.

--task: t2v-A14B
- --dataset_config: dataset/dataset.toml
- --mixed_precision: fp16
- --fp8_base
- --xformers
- --optimizer_type: adamw8bit
- --gradient_checkpointing
- --learning_rate: 3e-4
- --max_train_epochs: 100
- --gradient_accumulation_steps: 1
- --seed: 5
- --optimizer_args: weight_decay=0.1
- --network_module: networks.lora_wan
- --network_dim: 16
- --network_alpha: 16
- --lr_scheduler: polynomial
- --lr_scheduler_power: 8
- --lr_scheduler_min_lr_ratio: "5e-5"
- --output_dir: output
- --save_every_n_epochs: 10
- --timestep_sampling: shift
- --discrete_flow_shift: 1.0
  For High-Noise Training:
- --min_timestep: 875
- --max_timestep: 1000
  For Low-Noise Training:
- --min_timestep: 0
- --max_timestep: 875

cyberbol•8/8/25, 2:27 PM

Today will try in diffusion pipe.

JonkoXL•8/8/25, 2:40 PM

probably the epochs and learning rate can be tweaked for faster results, ill try it out

JonkoXL•8/8/25, 2:40 PM

can you post some results after training?

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•8/8/25, 7:34 PM

I trained lora on a real person and still get plastic skin and plastic face in comfyui....what am I doing wrong here

Sskyrrr Hey does anyone tried a full finetune with Flux Krea ? Any samples to share/insi...

Furkan Gözükara SECourses•8/9/25, 10:55 AM

it works with our configs

Furkan Gözükara SECourses•8/9/25, 10:55 AM

people tested but i didnt have chance yet on vacation

FFurkan Gözükara SECourses people tested but i didnt have chance yet on vacation

skyrrr•8/11/25, 12:36 PM

Well deserved ! Enjoy your holidays

JonkoXL•8/11/25, 4:13 PM

@Furkan Gözükara SECourses
For Musubi Tuner Wan 2.2 training, you can add the following arguments to the accelerate command, to make it generate samples

--sample_prompts prompt.txt --sample_every_n_epochs 1 --sample_at_first

In the promp.txt file you can add the positive prompt, and also some arguments (within that textfile!)

A blonde girl dancing --w 640 --h 480 --f 1 --d 1 --s 20 --n blurry

JonkoXL•8/12/25, 8:33 PM

Anyone else trainign Wan 2.2. and somehow realizing the plugging the Lora for the low model into the high model and the Lora for the high model into the low model, giving you better results?

JonkoXL•8/12/25, 8:34 PM

I checked the MD5 hash with the Hugging Face page, it's strange..

JJonkoXL Anyone else trainign Wan 2.2. and somehow realizing the plugging the Lora for th...

Furkan Gözükara SECourses•8/12/25, 9:57 PM

wow weird

FFurkan Gözükara SECourses wow weird

JonkoXL•8/12/25, 9:59 PM

Yes, but managed to get my Cartoon style Lora finished today

JonkoXL•8/12/25, 9:59 PM

https://civitai.com/models/1862320/wan22-t2v-lora-cartoon-style

(Wan2.2 T2V Lora) - Cartoon Style - Wan 2.2 T2V LORA - Low | WanVid...

(Wan2.2 T2V Lora) - Cartoon Style Create Cartoon Style images and videos. (see examples) Use "r3tr0c0m1c" and "cartoon" as a prompt keyword. Resolu...

JonkoXL•8/12/25, 10:06 PM

JonkoXL•8/12/25, 10:21 PM

JonkoXL•8/12/25, 10:23 PM

JJonkoXL https://civitai.com/models/1862320/wan22-t2v-lora-cartoon-style

Furkan Gözükara SECourses•8/12/25, 10:28 PM

nice

FFurkan Gözükara SECourses nice

JonkoXL•8/12/25, 10:35 PM

Thanks!
Wan 2.2 is very cool, my favorite model to play with.
I just wish they would launch a controlnet version for 2.2 already.

JonkoXL•8/12/25, 10:39 PM

My results so far is 3000 steps for 25 images at 2e4 learning rate, on dim 32 alpha 24, trained on 720x720 resolution.
Just a bit less than 2 hours training per model on my RTX 5090 without any offloading.
Lora strength of 1 works for 960x720 and 720x480. Needs a higher strength for higher res or if prompt gets too long.

like if i wanted to train the same dataset with the same settings but different base models (for a l

Similar Threads