Home
Creators
Search Recent Missing Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register Favorites Keys Review DMs Logout
Community
Telegram ThePornDude
Home Creators Posts Import Register Favorites Logout

AI‑Toolkit WAN LoRA Training Ultimate Pack (Patreon)

Published:
2025-07-20 16:50:35
Edited:
2025-07-20 23:02:27
Imported:
2026-06
Tags:

Downloads

Content

Hey everyone! I’ve made a new video for the “ULTIMATE WAN LORA TRAINING AI‑TOOLKIT WEBUI.” Hands‑down the BEST AI model training I have ever made! VIDEOS & IMAGES!!!Just fricking insane! This really is the best Ai model currently available and Ai-Toolkit makes training a Lora super ultra easy as well, basically the ultimate combination, perfect for complete beginners! With it you can train any LoRA you want for WAN: people, styles, and even full video LoRAs… it’s just nuts!

You can watch the full video here: https://youtu.be/lRg5sPBXTZE

I’ve also make a 1‑click installer for both Local AND RunPod setups just for Patreon supporters right here: https://www.patreon.com/posts/134551276

Link for the manual install: https://pastebin.com/UQNL51Z2Down below you will also find the WAN_XY-PLOT_LORA_TESTING.json for free for you to use!

Below you’ll find the LoRAs I trained in the video—free for you to play with:

Margot Robbie LoRA

----Taken down (by myself just in case) send me a message for more info

Jojo's Bizarre Adventure Style LoRA

https://huggingface.co/Aitrepreneur/test/resolve/main/hirohiko-araki-style_W.safetensors?download=true

Vlog Style LoRA

----Still in training, come back later....

As always, supporting me on Patreon allows me to keep creating helpful resources like this for the community. Thank you for your support - now go have some fun😉!

Files

Comments

Jay

Since I have Linux do I use the rubpod.sh version?

Shinichi

Is this a JoJo reference 🤭😉

Aitrepreneur

No it's for runpod only, altough it might work on linux if you have an already existing comfyui install

Boyo's Medicine (edited)

Comment edits

2026-09-08 20:00 @aitrepreneur, I love your stuff but your recent video on Margo Robbie with Wan is actually breaking Australian law. Australian law has actually fined people 50m in fines each for doing what you did as you are explicitly demonstrating how to do it and showed the world with a person who is protected massively under Auz law. I am a specialist in this area so I know my onions. US people fine as they have no laws covering them but UK EU , Auz you are in massive danger by doing what you just did in that video. If you want to know the exact laws just get in touch and I can explain. No this is not a sales pitch , I do not want you to end up in jail or fined out of existence.
2025-07-20 22:03

Defp

I'm curious if anyone tried training a LoRA on a character or concept with images as a single frame, then using it to generate a video?

HQKRD

Hi, can you guide us how to make the downloading process work? I see alot of people including me couldn't get the model downloaded after after starting the Job. It always got stuck and will not resume at any point. You help will be much appreciated.

Tetsuo Oshima

Hi K, I think you forgot something very important in the video tutorial : Max Step Saves to Keep, is at 4 by default. Meaning even though you can see the progression with the image samples, you're gonna get only the last 4 epochs so it better not be overtrained... or you are fucked. This is my first lora training using Runpod, it's still going while I'm typing this, we'll see x) I'm training a quite difficult anime style with only 33 images, so far I also noticed something else : The LightX2v lora might help giving very clean results in only 10 steps, but it kills the style. 20 steps without LightX2v is a lot closer to the original style

Aitrepreneur

That is very true and that was a huge mistake on my part, I realized it once the video was already uploaded.... also for the style, I use the fusionx model and lightx lora at 0.3-0.4 weight to add more contrast. I also found that using the normal model with fusionx lora at 1.5 weight and lightx lora at 0.8 gives great looking results depending on the style, so I suggest playing a little bit with the loras weights

Marcus LeVere (edited)

Comment edits

2026-09-08 20:00 When I updated COMFYUI I got: The update for the following custom nodes has failed: comfyui_tinyterranodes Do I need to worry?
2025-07-23 18:45

Aitrepreneur

just click on the manager button on the top right, click on missing custom node and install the missing node, if a node has import failed message, just uninstall it, restart and then reinstall it

RealAri

What image aspect ratio/size should we use for training Lora’s?

Aitrepreneur

Doesn't matter, just make sure your images are of high quality and high resolution , preferably above 1024x1024

Bob Winberry

I did exactly as you suggested, but still getting: Traceback (most recent call last): File "C:\AITOOLKIT\ai-toolkit\run.py", line 6, in from dotenv import load_dotenv ModuleNotFoundError: No module named 'dotenv'

Arona

Getting the error "validate_prompt() missing 1 required positional argument: 'prompt'" pm tje Lora Testing workflow every time, I of course, have a prompt in. What am I doing wrong? # ComfyUI Error Report ## Error Details - **Node ID:** 77 - **Node Type:** ttN advPlot images - **Exception Type:** TypeError - **Exception Message:** validate_prompt() missing 1 required positional argument: 'prompt' ## Stack Trace ``` File "/workspace/ComfyUI/execution.py", line 427, in execute output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/ComfyUI/execution.py", line 270, in get_output_data return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/ComfyUI/execution.py", line 244, in _async_map_node_over_list await process_inputs(input_dict, i) File "/workspace/ComfyUI/execution.py", line 232, in process_inputs result = f(**inputs) ^^^^^^^^^^^ File "/workspace/ComfyUI/custom_nodes/comfyui_tinyterranodes/ttNpy/tinyterraNodes.py", line 2662, in plot plot_image, images, samples = plotter.xy_plot_process() ^^^^^^^^^^^^^^^^^^^^^^^^^

Tetsuo Oshima

Thanks I tried the normal model but with lightX it was way too saturated so I use the FusionX lora only, at 1.40. I adjusted the MagCache according to the doc on Github, it gave slightly lower quality, slightly slower gen time but more fine details so it's still interesting because I upscale in the end anyway. I made many mistakes for that first training so it cost me around 7.50$... For example I think if you forget to STOP the pod once training is finished, the money continue to decrease x) And 10 samples every 250 steps is too much, each image take 50 seconds to generate, total 210 samples=3 hours, huge waste of time lol the actual training was only 3 hours... Also I trained up to 5000 steps like you advised in the video, but at 3000 it's already quite good and maybe even before, so that's a ton of epochs that all gives a good result; choosing one is a total nightmare for me, that's the part I really hate with Lora training in general x)

Bruce

Same :(

Aitrepreneur

Same thing as I said before, this error is due to an incorrect install “Desktop development with C++" really make sure you got it installed correctly. Download “Build Tools for Visual Studio 2022” https://visualstudio.microsoft.com/visual-cpp-build-tools/ During the setup, tick “Desktop development with C++” then click Install Then restart your pc, and redo the install in a new folder.

Aitrepreneur

Yup, it's all about testing, testing, testing and experience, hence why my videos take so long to make 😅 and this is just the bare minimum. For the lightx lora, I like using it to actually ADD more contrast to the images depending on the style but you don't have to use it for everything. Some loras need more weight, some loras need less, it's all about testing to see which results do you actually prefer.

Arona

works perfectly, thank you again!

LW

Hi K, I'm also getting the ModuleNotFoundError: No module named 'dotenv' error. I have downloaded “Build Tools for Visual Studio 2022” from https://visualstudio.microsoft.com/visual-cpp-build-tools/ “Desktop development with C++” is checked and Build Tools is installed and updated. I then did a clean install using your one-click installer in to a new folder. Not sure why this is not working

LW

I tried specifically installing dotenv and adding the path to the system environment variables and restarting but still the same error.

LW

I also noticed that I had Build Tools for Visual Studio 2019 installed. I wondered if that was causing confusion so I uninstalled the 2019 version then restarted the computer and tried to run the AItoolkit but got the same dotenv error

Aitrepreneur

dotenv error is indeed an issue caused by the absence of the Desktop development with C++ Make also sure that you have python 3.11.10 and that it is added to path and that you have the latest version of nodejs installed + the correct cuda toolkit for your GPU. Then you can also try going inside the folder install, click on the folder path type cmd press enter, this will open a cmd window inside the folder and inside type: venv\Scripts\activate pip install -r requirements Press enter and then wait until everything is installed then relaunch the launcher

LW

Thanks for the reply. So, on the last step.... pip install -r requirements, I got the following: (venv) X:\imageLoraTraining\ai-toolkit>pip install -r requirements ERROR: Could not open requirements file: [Errno 2] No such file or directory: 'requirements' so typed: pip install -r and got:- (venv) X:\imageLoraTraining\ai-toolkit>pip install -r Usage: pip install [options] [package-index-options] ... pip install [options] -r [package-index-options] ... pip install [options] [-e] ... pip install [options] [-e] ... pip install [options] ... -r option requires 1 argument The question is what requirements argument am I supposed to enter? Sorry for being such a computer dodo :)

LW

I think I'm going to have to try that. Just a bit worried that other programs might stop working that need python 3.13

Ostap222

Hi, is it better than diffusion pipe?

Boxertwin

As I couldn't get the AI Toolkit to run locally, I tried runpod. However, after following all your instructions, when I pasted the 2 lines of code to install the toolkit I get this message "chmod: cannot access 'WAN2_2-ULTRA-AUTO_INSTALL-RUNPOD.sh': No such file or directory bash: ./WAN2_2-ULTRA-AUTO_INSTALL-RUNPOD.sh: No such file or directory root@cdd7502691c6:/workspace# "

m16akm

Wan 2.2 support? :)

#DFined

As far as I can see, they are just straight up intercompatible. At least my 2.1 character loras worked fine with 2.2 with no modifications

#DFined

Its honestly kinda unbelievable how willingly Wan 2.x seems to learn. Compared to training on one of the sdxl finetunes - this is just a breeze! Thanks for the awesome guide

Vincent Nestler

XY plot not working for me ttN advPlot images object of type 'NodeOutput' has no len() Tried to troubleshoot with perplexity. Seems to suggest that at this point just not compatible. I am running this on a 5090 Thoughts?

newtoai

Hi. How do I start the ai-toolkit program locally after installed it on my pc? Thanks!