Posts

Showing posts with the label LoRA

Can AI Write Your LoRA Captions? Three AIs on 88 Drawings

Image
Can AI write your LoRA captions for you? Yes, but I had three AIs cross-check 88 drawings because one AI alone missed things. I'm Labo, the lighthouse keeper. Today's question is whether you can let AI write your LoRA captions , the little txt file that sits next to every training drawing. I had Claude, GPT and Grok check each other's captions for 88 drawings for a line-art LoRA. What that taught me most: a word that wasn't in the captions won't work in the prompt either. One short line of text for every drawing, and three readers looking at it. Last time we taught the body on its own. The student, whose dad draws webtoons and never gets a day off, wants to help him draw his manga with AI at home . Today she came with her notebook open.

LoRA Breaking the Body? A Separate Anatomy Dataset First

Image
LoRA keeps breaking the body of your character? Train a separate anatomy dataset first, so the body is learned apart from the outfit style. I'm Labo, the lighthouse keeper. Today's page is about what I did when my LoRA kept breaking the body : I split the training into two sets, one of outfit drawings for the style and one where only the structure of the body shows, and taught the body on its own. If you want a consistent character across panels , this is the step that finally worked for me. What I took from it: I think the body comes before the clothes. Put the outfits aside for a day and look at the frame underneath. Last time I ended with "teach the body separately," and the student said it the moment she opened the door. Her dad draws webtoons with no days off, and she's learning to draw manga with AI at home to help him.

Why a Consistent AI Character Changes With Every Outfit

Image
Why does a consistent AI character look different in every outfit with the same LoRA? Outfit changes can pull the face away from the character. I'm Labo, the lighthouse keeper. Today's page is about the day my trained LoRA drew the same character, but she looked like a different person in every outfit , and the full-body shots fell apart too. If you want a consistent character across panels , this is the wall. My guess from that day: change the outfit, and the AI stops seeing the same person. She only changed clothes, and somehow she became a stranger. The student came in looking pleased. Her dad draws webtoons and never gets a day off, so she's learning to draw manga with AI at home and take a few tired steps off his hands.

LoRA Epoch 4 vs Epoch 6 Look the Same? img2img vs txt2img

Image
LoRA epoch 4 and epoch 6 drawing the same picture? Then the LoRA is not being applied, and img2img versus txt2img is the place to check. I'm Labo, the lighthouse keeper. Today: why my LoRA epoch 4 and epoch 6 files drew the same picture , and how that taught me the difference between img2img and txt2img the hard way. What I learned: if different epochs give the same result, the LoRA isn't working at all. Two files with different names, two pictures exactly alike. Last time we wired the ComfyUI default workflow, and I mentioned getting lost over one box, denoise. The student, whose dad is a Korean webtoon artist with no days off, is learning this to help him draw his manga with AI at home . She sat down with last time's question.

My First LoRA Drew Something Else: Picking Training Images

Image
My first LoRA drew something I never asked for. Here is how picking the wrong training images caused it and what to check before training. I'm Labo, the lighthouse keeper. This is my notebook of drawing manga with AI on a home computer, and today's page is about my first LoRA — the one that came back with pictures I never asked for. If you want a consistent character across panels , this mistake is worth knowing before you train anything. The student walked in holding a fresh set of LoRA files and asked, "Now I just plug these in, right?" The day I tried my first LoRA, the screen showed something completely different from what I had in mind.

Renting a RunPod GPU for Kohya LoRA: Stop Isn't Terminate

Image
Renting a RunPod GPU for Kohya LoRA training? Press Stop when you pause, but only Terminate ends the billing for the whole pod. I'm Labo, the lighthouse keeper. Today is RunPod for the first time : renting someone else's GPU by the hour to run a Kohya LoRA training, and every place I got lost on my first try. The student came in with the RunPod sign-up page open: "Do I just press this?" The day we borrow one graphics card from somewhere above the clouds. Her dad draws webtoons and barely gets a day off, so she's learning to draw manga with AI at home .

SDXL LoRA Training at 52 Seconds a Step? It Was 16GB of RAM

Image
SDXL LoRA training stuck at 52 seconds a step? The slow part was my 16GB of RAM, not the graphics card. I'm Labo, the lighthouse keeper. Today is about why my SDXL LoRA training crawled at 52 seconds a step on my home computer, and why the culprit wasn't the graphics card but 16GB of RAM. If you want to draw your own manga with AI at home , here's what that night taught me: when it's slow, don't guess the culprit. Find it in the numbers. The expensive part gets suspected first. The clue was somewhere cheaper. The student came in still thinking about last time. Her dad draws webtoons and never gets a day off, and she's learning this so she can teach an AI his style one day and give him some time back. Student: Labo, you said you'd run it again with SDXL that night. Did it work? Labo: I switched the base model to AlbedoBase XL and left the training running overnight. The screen said 51.89s/it . That's 52 seconds for one step. To reach the end, i...

LoRA Trained for 56 Minutes, No Style: The AI Never Looked

Image
LoRA trained for 56 minutes with no style showing? The AI never actually looked at the drawings, so it guessed the style. I'm Labo, the lighthouse keeper. My first LoRA training ran for 56 minutes and the style still didn't come out, and today I show the student exactly why. If you want to draw your own manga with AI at home , this is the mistake worth skipping: an AI that never looked at the drawings guessed the style from a genre name. Pretty, but not the style. The question is why. The student had been chewing on it since last time. Her dad draws webtoons and never gets a day off. She's learning all this so that one day she can teach an AI his style and take some of the repetitive work off his desk. Before she gets there, she wanted to know exactly where my first run went wrong.

First Kohya LoRA Done, Style Missing? Checking It in SwarmUI

Image
Kohya LoRA training finished but the style is missing in SwarmUI? A run that ends does not mean the style showed up. I'm Labo, the lighthouse keeper. Today is a first LoRA training run in Kohya, from the boxes you fill in to the moment you check the result in SwarmUI, all on a computer at home. The thing that day taught me: a training run that finishes is not the same as a style that shows up. Five files on the desk, and one question: is the style in there? The student came back the day after we picked the practice drawings and wrote the captions. Her dad draws webtoons and never gets a day off, so she's learning this to help him draw his manga with AI at home , one tired step taken off his hands at a time. Today she opened Kohya and froze. Student: Labo, there are so many boxes. Where does everything go?

How Many Drawings to Train a LoRA? Picks, Captions, Trigger

Image
How many drawings do you need to train a LoRA? Fewer than you think, as long as each one passes your rules. I'm Labo, the lighthouse keeper. When you want to draw your own manga with AI at home , the first real job isn't the program. It's deciding how many drawings to train a LoRA on, and which ones. What I learned the hard way: the drawings you need aren't the most, they're the ones that pass the rules. A USB stick full of drawings, and the question of which ones go in. A day after Kohya finally opened on her computer, the student came back with a USB stick. Her dad's drawings, a lot of them. He draws webtoons, and she wants to teach an AI his style so he gets a little time back. Student: Labo, do I just put all of these in? Labo: No. Today is about picking. But one promise first: an artist's drawings are private. In a Korean webtoon studio they're the work itself. So we'll practice on a set I made separately. The rules are the same.

Draw Manga with AI at Home: LoRA, ComfyUI and ControlNet Map

Image
Want to draw manga with AI at home using LoRA, ComfyUI and ControlNet? Start with a map of the tools before installing anything. I'm Labo, the lighthouse keeper. If you want to draw your own manga with AI at home , the first thing you need isn't a program. It's a map. The student came in this morning, laptop under her arm, and said she had installed "everything" last night and now couldn't tell what any of it was. One island, one program. Today we only draw the map. Some background: her father draws webtoons for a living, and he works late every night. She wants to learn AI so she can take some of that load off him.

Browse by topic

Latest posts

    See every post