Software Engineering Courses (SECourses)•5mo ago

I'm currently training a test LORA on the wan22 low noise model, specifically a LORA for a person or

I'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.

Ccyberbol I'm currently training a test LORA on the wan22 low noise model, specifically a ...

AiInfluence•8/4/25, 3:13 PM

lmk how it went

AiInfluence•8/4/25, 3:13 PM

I tried wan 2.2 t2i and I was very disappointed

AiInfluence•8/4/25, 3:13 PM

text was all wrong and textures / quality same as krea

cyberbolOP•8/4/25, 3:13 PM

I will

Ccyberbol I will

AiInfluence•8/4/25, 3:14 PM

is this musubi

cyberbolOP•8/4/25, 3:15 PM

Diffusion-Pipe - best for me. using many times and created many nice Loras for wan2.1

cyberbolOP•8/4/25, 3:15 PM

https://civitai.com/articles/12837/full-setup-guide-wan21-lora-training-on-wsl-with-diffusion-pipe

cyberbolOP•8/4/25, 3:16 PM

https://tensor.art/u/842260292657429385/models

CyberAImania's Models

JJonkoXL For Wan2.1 T2V using (25 videos) 480x360@61 and (23) images 960x720 fits jus...

Furkan Gözükara SECourses•8/4/25, 4:05 PM

nice

Ccyberbol Yesterday, I extracted a LORA from my Dreambooth model (of my character) that I ...

Furkan Gözükara SECourses•8/4/25, 4:05 PM

i think kohya lora extraction is not working accurate

Joony•8/4/25, 10:41 PM

anyone know how to upload finetuned flux dev model ( dreambooth style ) to replicate so i can call it with a api?

JJoony anyone know how to upload finetuned flux dev model ( dreambooth style ) to repli...

Furkan Gözükara SECourses•8/5/25, 9:08 AM

check this

Furkan Gözükara SECourses•8/5/25, 9:08 AM

https://replicate.com/fofr/any-comfyui-workflow

fofr/any-comfyui-workflow – Replicate

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

Furkan Gözükara SECourses•8/5/25, 9:08 AM

we had requested base model support i am not sure if he added

dschulie•8/5/25, 8:26 PM

can i run multiple instances of onetrainer(gui) or at least cmd? because i don't seem to find any batch processing in the interface

dschulie•8/5/25, 8:27 PM

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?

dschulie•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

dschulie•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

dschulie•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

dschulie•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?

cyberbolOP•8/7/25, 7:37 PM

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

cyberbolOP•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?

cyberbolOP•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

cyberbolOP•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?

I'm currently training a test LORA on the wan22 low noise model, specifically a LORA for a person or

Similar Threads