Software Engineering Courses (SECourses)•5mo ago

Anyone else trainign Wan 2.2. and somehow realizing the plugging the Lora for the low model into the

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?

JonkoXLOP•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

JonkoXLOP•8/12/25, 9:59 PM

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

JonkoXLOP•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...

JonkoXLOP•8/12/25, 10:06 PM

JonkoXLOP•8/12/25, 10:21 PM

JonkoXLOP•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

JonkoXLOP•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.

JonkoXLOP•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.

JJonkoXL My results so far is 3000 steps for 25 images at 2e4 learning rate, on dim 32 al...

Furkan Gözükara SECourses•8/12/25, 10:42 PM

nice info thanks

Newtus•8/13/25, 5:39 AM

I was interested in creating a Chorma lora using Kohya SD scripts. I'm thinking the issues I'm having are just my ignorance of command line. Does anyone know of a youtube or idiots guid for Kohya SD-SCripts? It's probably too much to ask for Chroma training, but if there was a Flux I think I can learn on that and eventually wing it. Thanks.

NNewtus I was interested in creating a Chorma lora using Kohya SD scripts. I'm thinking ...

JonkoXLOP•8/13/25, 6:51 AM

what does your command look like?

NNewtus I was interested in creating a Chorma lora using Kohya SD scripts. I'm thinking ...

Furkan Gözükara SECourses•8/13/25, 7:17 AM

this is literally gui for kohya sd scripts

Furkan Gözükara SECourses•8/13/25, 7:17 AM

https://youtu.be/FvpWy1x5etM

YouTubeSECourses

FLUX Full Fine-Tuning / DreamBooth Training Master Tutorial for Win...

If you want to train FLUX with maximum possible quality, this is the tutorial looking for. In this comprehensive tutorial, you will learn how to install Kohya GUI and use it to fully Fine-Tune / DreamBooth FLUX model. After that how to use SwarmUI to compare generated checkpoints / models and find the very best one to generate most amazing image...

FFurkan Gözükara SECourses this is literally gui for kohya sd scripts

AiInfluence•8/13/25, 7:17 AM

im getting very bad results

AiInfluence•8/13/25, 7:18 AM

on wan 2.2 preset not working

JJonkoXL what does your command look like?

Newtus•8/13/25, 7:21 AM

Thank you in advanced. I'm almost ashamed to post it for fear I forgot something simple. I put the read me into chatgpt to try and help me create the command line and the dataset.toml file: accelerate launch --mixed_precision bf16 --num_cpu_threads_per_process 1 flux_train_network.py ^
--pretrained_model_name_or_path "D:/APPS/KohyaSD/TestModels/Chroma.safetensors" ^
--clip_l "D:/APPS/KohyaSD/TestsModels/clip_l.safetensors" ^
--t5xxl "D:/APPS/KohyaSD/TestModels/model-00001-of-00002.safetensors" ^
--ae "D:/APPS/KohyaSD/TestModels/diffusion_pytorch_model.safetensors" ^
--model_type chroma ^
--apply_t5_attn_mask ^
--cache_latents_to_disk ^
--save_model_as safetensors ^
--sdpa ^
--persistent_data_loader_workers ^
--max_data_loader_n_workers 2 ^
--seed 42 ^
--gradient_checkpointing ^
--mixed_precision bf16 ^
--save_precision bf16 ^
--network_module networks.lora_flux ^
--network_dim 4 ^
--network_train_unet_only ^
--optimizer_type adamw8bit ^
--learning_rate 1e-4 ^
--cache_text_encoder_outputs ^
--cache_text_encoder_outputs_to_disk ^
--highvram ^
--max_train_epochs 4 ^
--save_every_n_epochs 1 ^
--dataset_config "D:/APPS/KohyaSD/TestCFG/C4TS_dataset_multi_bs.toml" ^
--output_dir "D:/APPS/KohyaSD/TestOutput" ^
--output_name chroma-lora-name ^
--timestep_sampling shift ^
--discrete_flow_shift 3.1582 ^
--model_prediction_type raw ^
--guidance_scale 1.0

JonkoXLOP•8/13/25, 7:23 AM

Whats the error you get?

JonkoXLOP•8/13/25, 7:25 AM

I think the --t5xxl needs to be a single safetensor file or pth file, and not a partial file (00001 of 00002)

JonkoXLOP•8/13/25, 7:25 AM

Also discrete_flow_shift maybe rounded number?

JonkoXLOP•8/13/25, 7:26 AM

did you manually edit the datset.toml? how does it look?

AAiInfluence on wan 2.2 preset not working

Furkan Gözükara SECourses•8/13/25, 7:29 AM

which preset exactly you using?

Newtus•8/13/25, 7:34 AM

Yes, I edited the toml file. Also I am working off a 4090. It looks like it attempts to run. I get the error: File "D:\APPS\KohyaSD\sd-scripts-sd3\venv\lib\site-packages\torch\nn\modules\module.py", line 1362, in convert
raise NotImplementedError(
NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.
Traceback (most recent call last):
File "D:\PROG\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None, and Toml: [general]

Common settings for the dataset

flip_aug = true
color_aug = false
keep_tokens_separator = "|||"
caption_extension = ".txt"

[[datasets]]

This is the dataset definition for training

batch_size = 2
enable_bucket = true
resolution = [1024, 1024]

[[datasets.subsets]]
image_dir = "D:/APPS/KohyaSD/TestIMG/10_C4TS cats"
num_repeats = 1 A suggestion from chatgpt was to move to bf16. (on the two lines in the bat file) I changes that is and looks like it attempts to load the models. But then another set of errors. It's like moving from one set of issues to another and I'm afraid I'm just working in the wrong direction.

NNewtus Yes, I edited the toml file. Also I am working off a 4090. It looks like it atte...

Furkan Gözükara SECourses•8/13/25, 7:43 AM

you are trying to train flux?

Newtus•8/13/25, 7:48 AM

No, I would ultimately like to train Chroma.

NNewtus No, I would ultimately like to train Chroma.

Furkan Gözükara SECourses•8/13/25, 7:50 AM

you can use gui

Furkan Gözükara SECourses•8/13/25, 7:50 AM

and add some extra params

Furkan Gözükara SECourses•8/13/25, 7:50 AM

https://github.com/kohya-ss/sd-scripts/pull/2157

GitHub

Feature Chroma support by kohya-ss · Pull Request #2157 · kohya-s...

Thank you lodestones for the high quality model.
--model_type option is added to flux_train_network.py. For Chroma, --model_type chroma is required.
According to lodestones, --apply_t5_attn_mask --...

FFurkan Gözükara SECourses you can use gui

Newtus•8/13/25, 7:51 AM

Thank you I will review that.

Sakami•8/13/25, 7:51 AM

Hey Doc @Furkan Gözükara SECourses
Are there any plans for Fine-Tuning or LoRA for Wan2.2? If not in the near future, where would you recommend looking to learn more about that field?

SSakami Hey Doc @Furkan Gözükara SECourses Are there any plans for Fine-Tuning or LoRA ...

Furkan Gözükara SECourses•8/13/25, 7:51 AM

yes i plan first qwen image then wan 2.2

Sakami•8/13/25, 7:52 AM

thank you

Furkan Gözükara SECourses•8/13/25, 7:52 AM

also will publish results of flux dev vs flux krea dev

Furkan Gözükara SECourses•8/13/25, 7:52 AM

today . generating massive grid

Furkan Gözükara SECourses•8/13/25, 7:52 AM

FFurkan Gözükara SECourses which preset exactly you using?

AiInfluence•8/13/25, 7:58 AM

wan 2.2 lightx2 lora

AiInfluence•8/13/25, 7:58 AM

but i want to switch to kijai new not the wan 2.1 old

AiInfluence•8/13/25, 7:58 AM

you need to update

AAiInfluence wan 2.2 lightx2 lora

Furkan Gözükara SECourses•8/13/25, 8:00 AM

which one here? also i will update wan 2.2 presets soon after testing new loras hopefully

Furkan Gözükara SECourses•8/13/25, 8:01 AM

NNewtus Thank you I will review that.

Furkan Gözükara SECourses•8/13/25, 8:04 AM

i can also make chroma workflow i think

AiInfluence•8/13/25, 8:22 AM

this

AiInfluence•8/13/25, 8:22 AM

AiInfluence•8/13/25, 8:22 AM

needs update

AiInfluence•8/13/25, 8:22 AM

with kijai lightning lora

AAiInfluence Click to see attachment

Furkan Gözükara SECourses•8/13/25, 8:28 AM

will check thanks

Furkan Gözükara SECourses•8/13/25, 8:29 AM

can you give link

FFurkan Gözükara SECourses also will publish results of flux dev vs flux krea dev

skyrrr•8/13/25, 8:33 AM

Very interested in your feedbacks before trying a full kra finetune. How many images for your test ?

FFurkan Gözükara SECourses will check thanks

Dr. Odin•8/13/25, 8:36 AM

just went through your video on the sdxl lora training with one trainer.. im new to one trainer.. barely a week old... i wanna pay for your patreon and wanted to ask if you updated the presets you mentioned.. i have about 60 images i wanna train them for a person but i cant find regularization images for a female.. so im abit stuck there

Anyone else trainign Wan 2.2. and somehow realizing the plugging the Lora for the low model into the

Common settings for the dataset

This is the dataset definition for training

Similar Threads

Similar Threads

Common settings for the dataset

This is the dataset definition for training

Similar Threads