LORA Training - for HYPER Realistic Results

preview_player
Показать описание
I set my goal to get the most realistic Lora results. A Lora that resembeles the Model in every little detail. My goal: To create images that can pass as actuall photographs of her. Here is what I leared in the Process.

#### Links from the Video ####

Model: Betka

00:00 Intro
00:18 Magical Solution
01:45 Image Selesction
07:21 Better Gear
13:01 Preparing Images
15:18 WD14 Clip Texts
16:15 Booru Dataset Manager
20:08 Folder Structure
21:21 Khoya ss Lora Settings
26:40 A1111 Lora Testing
Рекомендации по теме
Комментарии
Автор

I think this is the best, most detailed tutorial on the subject of training a character lora that I have seen. The information you have given has changed my lora's from treaining nightmare juice, to training actual people. Thank you so much for this.

numbnut
Автор

Thank you Olivio! I've had to train new faces and since Dreambooth isn't the "go-to" these days I've been looking for a new LORA tutorial. Those last 2 mins where you explain putting the LORA into the aDetailer really hit home - such an amazing workflow 👊💯

pixeladdikt
Автор

Realistic vision just updated a couple days ago and it looks fantastic!

JavierPortillo
Автор

I made a Lora of my dead grandma last night to create images of her for my mom, and she was very happy with it, but it was so blurry and unfortunately it isn't really possible to give it a better dataset anymore

ozerune
Автор

(16:40) First, he meant "ALT+F4". Second, you can "ALT+TAB" to swap to the alert popup. Also, BooruDatasetTagManager has hotkeys you can set yourself (under "settings" => "hotkeys"). The default hotkey for hiding the preview window is "CTRL+P".
(25:30) He forgot to mention that you can't set "max resolution" to 768x768 if your input images are less than that--say 512x512. A lot of times we'll create LoRAs specifically for use in image-to-image. That means we want those LoRAs to output at a low resolution so that it is quick and then you can "upscale" in img2img using the low-res as a base. You can also use 128x128 for pixel art.

WifeWantsAWizard
Автор

Olivio, absolute professional advice here that is really appreciated. I follow you for quite some time now and I have to say it really shows the earnesty in which you follow your passion and teach it to others. Bravo! Keep it up!

ArnoSelhorst
Автор

I can not stress enough how important the quality of the source images is for training Loras. This is one of the few tutorials which actually give useful advice how to create and prepare a high quality training data set.

Thank you for this outstanding video ❤

lennylein
Автор

Wow thank you for explaining the right way to set up samples… you are correct 👍 Sir!

JohnSmith-vkvq
Автор

BIG thank you! This was exactly the video I was missing in my LORA expeditions.

maxfahl
Автор

The new Kohya SS master release is using different tabs of your video : Deambooth, Loora, Text Inversion ... nothing Like Dreambooth TI, Dreambooth Lora, How to figure what tabs do what, since the dreambooth tab doesnt include anything like network rank ... Also the Lora tabs include nothing related to Dreambooth/Lora technique.

Nobody is talking about it but the dev of the GUI just changed the whole UI whithout providing any documentation on how to interpret all the changes to the GUI he has made.

axelesch
Автор

Thank you Olivio, this is a good process for getting a desired result. I used similar process of image preparation for making custom embeddings.

jrfoto
Автор

Thanks again. Very helpful, like always 🙏🚀

LeonvanBokhorst
Автор

Olivio, mind doing an update tutorial on making those dancing AI videos? I been trying but either the face is messed up or just stop doing the poses.

Inugamiz
Автор

Thank you for this very informational guide, Definitly -one if not- the best out there : )

AThijs
Автор

Hello! there is also a psychology factor, women do not like too detailed photos -)
that is, it is not necessary to see all the wrinkles, acne, pigmentation, etc.
so detailing is important for large details of the shape of the eyes, eyebrows, eyelashes of the lips
and if you focus on the super detailing of all wrinkles
- they will tell you - it doesn’t look like it!
no wonder the beauty industry works -)))

you can reduce the number of epochs by increasing the dataset, i.e. on a dataset of 50-60 photos .80-90 steps per photo
and one epoch give quite normal results, with the weight of lore in the prompt 0.7-0.8,
+ a variety of clothes, a variety of backgrounds
if the set is on the same background - this background will pop up in the most unexpected places if it is only in a white T-shirt
- this t-shirt will be everywhere,
it's better to cut out the background altogether,
I am from a set of 10 photos with the same type of background - I cut out the background for 8, well, a variety of clothes will not let sd get hung up on a certain color, style

TheTornado
Автор

Many thanks for this. Two questions. No 3.

What is about those extra images.. Some other youtubers suggest for the class of object.. Dont remember the name.. Calibration images?

When to make a lora and when to use dreambooth?


Third..
When i want to train for example the typical style an architectural company has for.. Lets say.. Office fassades seen from the street.. That for sure difffer often. But to still finde the essence of the style.. Lora or dreambooth. How many images. How to capption?

tomschuelke
Автор

As always, excellent work Olivio. I've been following you from Spain. My English is a bit limited, so I use an AI to translate your voice into Spanish based on the subtitles. It might be funny, but it's a lifesaver for me. You provide very detailed explanations in your videos. Greetings and thank you very much! 👏👏

AeroviewMenorca
Автор

21:03 "That number defines the steps or repetition [...]"
This number represents repetitions only (repeats).
steps is something else = nb.images x repeats.

21:09 "I mostly use 10 for my LoRA but others use 5 [...]"
Nothing's random in training a Lora ;) Number of repeats should more be about "how many images do I have for that specific LoRA", rather than about "how many epochs am I going to need now" or "I am used to that number".
Images found (let's say 100) x repeats (8) = 800 steps.
steps x gradient accumulate steps x epochs x regularization factor (if one uses properly made reg. images + reg captions for each trained image) = Max Train Steps.
800 x 1 x 2 x 2 = 3200 steps (which is often enough).

This being said I'm still confused about why or how one should balance repeats and/or epochs to reach the sweet spot between about 3K~4K Max Train Steps. Especially since we can save checkpoints and samples every N samples, run more epochs or resume from a precedent trained weight.

HanSolocambo
Автор

Alles schön und gut, aber die wirklich relevanten Stellen und Problematiken die einem beim Training begeegnen hast du nicht besprochen. Punkte die tatsächlich informativ gewesen wäre, sind: Was hast du geändert, nachdem ein LoRa die Kopfform oder Haare nicht richtig wiedergegeben hat? Welchen Unterschied macht die Auflösung und das Seitenverhältnis der Quellbilder sowohl in Trainingszeit, so wie auch in den Ergebnissen? Wie stellt man die Buckets richtig ein und wie ist deren Beziehung zur Trainingsauflösung und den Quellbildern? Wie trainiert man sowohl Portrait- wie auch Full-Body-Shots? Wie viele der jeweilig eingestellten Perspektiven haben bei dir funktioniert? 1 Teil Full-body, 3 Teile Close-up? Etwas anderes? Wie kann ich die Konsistenz der Ergebnisse in verschieden eingestellten Seitenverhältnissen verbessern/muss ich etwas bei den Quellbildern beachten damit die LoRas hier gut funktionieren? "Erklärungen" zu Mixed precision, Network rank dims (Dateigröße, Konsistenz der Ergebnisse), LoRa Auflösung sind bestenfalls als gefährliches Halbwissen zu bezeichnen und sollten auch dringend als solches markiert werden. Aussagen wie "Ich habe viele gute Ergebnisse bei mit fp16 trainierten LoRas gesehen, aber auch welche mit bf16" helfen keinem weiter und haben keine Aussagekraft für irgendwen, wenn die zugrundeliegenden Eigenschaften nicht zumindest kurz angeschnitten werden. Mein Vorschlag ist daher, entweder diese Punkte kennzeichnen als "persönlichen Eindruck" oder gleich sagen, dass man hier nichts objektiv nachweisbares weiß und nicht weiter recherchiert hat. Das Netz ist mittlerweile voll von "Tutorials" die zu 90% inhaltlich alle identisch sind und nur zu bestenfalls halbgaren Ergebnissen führen. Mehr Ehrlichkeit und oder echte Recherche wäre erfrischend hilfreich.

camar
Автор

Instead to create manually the folder for the training you can do it automatically using the Tools tab in the Kohya Dreambooth LoRA.
About the using of "Restore Faces" if I well remember in one of your video you suggested to don't use if you are using a LoRA model because it may modify the actual face. Actually I found that it may be true. When you use the Tools in Dreambooth there you set the key word for the LoRA and you also give a category to the model which is I believe important for the training.

Aviator-cehl