Posts

Showing posts with the label AI manga

Fixing AI Manga Faces with ComfyUI FaceDetailer: Not Solved

Image
ComfyUI FaceDetailer not fixing your AI manga faces? Mine still isn't fixed, so here is the unsolved attempt and my current guess. I'm Labo, the lighthouse keeper. Today's page is about AI manga faces: I tried to fix them with ComfyUI FaceDetailer, and it still isn't working. I'm showing it to you unsolved, just as it is. Here is the one thing I've learned so far: I think if you fix the face on its own, the face and the picture drift apart. A face looks natural only when it's born inside the picture. The harbor is in sight. We haven't reached it yet. This matters for anyone who wants a consistent character across panels . If the face doesn't belong to its picture, the same person won't look right from one panel to the next.

Why Is My AI Coloring Flat? Shaded Sketches vs Line Art

Image
Why does your AI coloring come out flat? A sketch with shadows already drawn in gives flat results, so use clean line art instead. I'm Labo, the lighthouse keeper. Today's page is the time my AI coloring came out flat: I gave the AI a sketch with the shadows already drawn in, and the render came back flat as paper. So I went back and pulled clean line art instead. If you want to draw your own manga with AI at home , here is what that taught me: I think when you give the AI a sketch with the shading drawn in, it paints it flat. So give the AI only the lines, and leave the shading to it. I shaded the sketch with care. What came back was flat as paper. The student came back still stuck on how last time ended. Her dad draws webtoons and never gets a day off, so she's learning this to help him. I'd mentioned my shaded sketch came out flat, and she couldn't let it go.

Sketch to AI Manga: Does ControlNet Scribble Keep Lines?

Image
Does ControlNet scribble keep the lines of your own sketch when turning it into AI manga? Scribble worked better for me than lineart mode. I'm Labo, the lighthouse keeper. Today's page is about how to turn your own sketch into manga with AI : putting a sketch into ControlNet scribble, and why I tried lineart mode first and came back to scribble. What I learned: half of a drawing style comes from the sketch. When the sketch is already the artist's, I don't force a style LoRA on top. The picture I used to describe in words, I now show in lines.

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.

What Are ComfyUI Nodes? Reading the Default Workflow

Image
What are ComfyUI nodes? Read the default workflow from the left, and the boxes and wires become a simple recipe in six steps. I'm Labo, the lighthouse keeper. Today: what a ComfyUI node is , and how the default workflow connects, box by box from the left. Read it in order and a node graph is just a recipe: ingredients (model), order slips (prompt), bake (KSampler), take out (VAE), serve (save). Six boxes joined by wires make one road to one picture. Last time we talked about keeping drawings on my own computer instead of AI art sites. In a Korean webtoon studio , unfinished pages are the work itself. So on June 5 I moved from SwarmUI to the engine behind its buttons, ComfyUI , sharing SwarmUI's model folder. The student, whose dad draws webtoons and never gets a day off, installed it herself; she wants to help him draw his manga with AI at home . Then she opened it.

Is It Safe to Upload My Drawings to AI Art Sites?

Image
Is it safe to upload your drawings to AI art sites? Once they reach someone else's server, they have left your control. I'm Labo, the lighthouse keeper. Today's question: is it safe to upload my drawings to an AI art site? And how FLUX licenses and an 8GB graphics card sent me back to my own computer. What I learned going the long way around: the moment you upload a drawing to someone else's server, it has left your hands. So I pick my own computer over convenience. Send the drawing across the sea to someone else's server, or keep it on the desk inside the lighthouse? The student's dad draws webtoons and never gets a day off, and she wants to help him draw his manga with AI at home .

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.

Why Does AI Art Need NVIDIA? CPU vs GPU and Minimum Specs

Image
Why does AI art need an NVIDIA graphics card, and can your PC run it? Four numbers on your spec sheet will tell you. I'm Labo, the lighthouse keeper. If you want to draw your own manga with AI at home , sooner or later someone tells you it has to be an NVIDIA card. Today the student asked me why, and the honest answer is that whether your PC can do it isn't written in any ad. Four numbers tell you. Before anything gets installed, one look at what's inside the computer. Last time I told her to open her Performance tab. She did. It's in Task Manager, and it shows the graphics card, its memory, and the computer's own memory on one screen. But she came in with a different question first. When she ran Kohya the other night, the black window kept printing one word: CUDA.

What Is Stable Diffusion? From a Company Server to Your PC

Image
What is Stable Diffusion? It is the AI drawing model that left a company server in 2022 and became a file on your own PC. I'm Labo, the lighthouse keeper. Before you draw your own manga with AI at home , it helps to know why that's possible at all. The short answer is Stable Diffusion , and the day in 2022 when an AI drawing model left the company server and became a file you could keep on your own computer. An AI that used to live only on a company server, now running on a desk at home. Last time I asked the student whether she had opened her Performance tab. She came back this morning and said she hadn't, on purpose. "Before I look at my computer, I want to know where all of this came from." Good order. If you know why a tool looks the way it does, you panic less when it breaks.

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