AI want to try both basic dreambooth and lora training
Fyou can do dual training with 2 cards
Fat the same time
ADepends how long it will take in the first place
ABTW how does one "properly" train a model? All tutorials seem to only show a scenario where you have like 50-150 photos and single prompt
MHi guys. I am struggling LoRA training in Dreambooth on Automatic1111. If I train a normal Dreambooth I get fairly good images. When I switch to LoRA the samples are okay but when I try a prompt with the LoRA it gives me completely random images. Is the extension broken or is it likely user error?
AI was under impression that with dreambooth I could make a large dataset (say 1000 images or more) and create individual prompts for each image that describes things from it I want to teach the model.
Fall you need is good images and captions
Flora is much harder
AYeah but in the extension there is single field for a prompt.
Frequires fine tuning of parameters
Fwatch this i explain logic of filewords
FYouTubeSECourses - Software Engineering Courses
Our Discord : https://discord.gg/HbqgGaZVmr. Newest update of DreamBooth extension of Automatic1111 brought huge quality and success improvement. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials...
AThanks.
Fi sent a dm to you if you be interested in
FHowdy! First of all I want to thank for all the great content provided in the YouTube channel. I've been watching a few to better understand the subject but I wonder which specific video or videos I should watch which is the most up to date if what I want to do is to use Stable Difussion with my own face with the best quality possible in Google Collab. I'd also like to do the same with a 2nd person. Should I train a 2nd model from zero or could I add the 2nd person to an already trained model? If so, how to do it for the best quality possible?
FI don't currently have an Nvidia card good enough for local
Fok i presume you cant pay to use runpod right?
Fso now i will list some tutorials for you
Fthis one how to train on colab
Fstill works
FYouTubeSECourses - Software Engineering Courses
Our Discord : https://discord.gg/HbqgGaZVmr. How to do free Stable Diffusion DreamBooth training on Google Colab for free. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, Automatic1111 and Goo...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Goo...
Fthis is a quicker and more up to date version of colab
Falso it shows more info about how to use colab path
FYouTubeSECourses - Software Engineering Courses
Our Discord : https://discord.gg/HbqgGaZVmr. This is the video where you will learn how to use Google Colab for Stable Diffusion. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, #Automatic1111...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, #Automatic1111...
Fthis is my newest dreambooth settings comparison but it uses web ui
FYouTubeSECourses - Software Engineering Courses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Web UI DreamBooth got epic update and we tested all new features to find the best settings (10). If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of...
https://www.patreon.com/SECoursesPlaylist of...
Fand this is a massive tutorial that explains concepts of dreambooth
FYouTubeSECourses - Software Engineering Courses
Our Discord : https://discord.gg/HbqgGaZVmr. The most advanced tutorial of Stable Diffusion Dreambooth Training. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, Automatic1111 and Google Colab ...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Google Colab ...
Fteaching 2 faces into 1 dreambooth model is a bit problematic. if they are different gender can work but if same gender
Fthen you should not use classification images to not bleed
JHi professor, have your trained lora with Kohya's webui
JI see a lot of videos talking about that
JI trained a lora with it and applied to the sd1.5
Jnothing happend
JKohya's lora also modifies the unet, which other loras from civitai does not have
Nwhat do you mean by "your dataset"? certainly it depends on the quality of your pictures. but as long as you have (like the pictures that you are used to take for your comparisions) simialar pictures you can compare f.e. 3, 6, 10, 20, 35, 50 pictures for training to find out how near the different trained images come to the "original" person..
Sthe number of pictures really does not matter for "accuracy", but it matters for variety, you can train with one single image, and have that exact look on all your outputs
Nah, that makes sense. so the effects is similar to overtrainig as an overtrained image shows mainly the unchanged input images
Syou cant overtrain a lora
Nok- i did not refer to lora in my main question
Soh that wasnt you, ok then.. well yes you can put something in your sanity text field that has nothing to do with your subject or like a specific style
Sand when that dissaplears from the samples, you overtrained
Nyes.
SI think there are several understandings of what overtraining is. you can overfit by destroying your subject. Like deform it. and you can overtrain by making it not flexible
Sbut I wonder why people would train a model baked into a checkpoint, you by default make it non flexible
Ni simply save at a alow epoch frequence so I can later compaare how good the single checkpoints are
Sthats not my point
Syou have a checkpoint thats good for one thing but not another