Hi, thank you for this tutorial and all your content. Could i use vertical and horizontal different resolutions?, for example, 384 x 576 px (for portrait images)
I have only ever trained with square images... I have heard that people do use different ratio images while training, but I think all the pics need to be same ratio.... I think the trick is to continue training by adding more steps with all new images - but again, I have not tried it.
I get best results from head/face shots (include eyebrows to top of shoulders) different angles, expressions, and lighting/environment. My pics are cropped square 2048x2048, rendered from 3D software.
Thanks, There’s hardly any info about Draw Things. So everything you post is really a valuable resource. How many images do you use for the training? Or what do you say is the minimum or maximum that makes sense. Also, would you suggest training of 1.5 Lora for people with only 16 GB of ram or use SDXL with 512 x 512? Thanks for the great content.
I think you can do 512x512 XL on 16GB, but it will be slow because the memory will sometimes need to swap to the hdd. Shut down all other apps, especially web and Discord. number of pics is maybe between 5 and 25 (mine was 27 here), more pics will increase RAM so use your best images.
I think so, just reload the LoRA by name and the settings should fill-in as before. Then you can change the photos and set the training steps higher to resume... But also consider it might be easier to start a new training session and create multiple LoRA - rather than over-training a model you like with extra garbage.
Thank you for the really helpful tutorial. I tried to train my own LORA with 12 photos and managed to get the captions, but every time I start the training the program crashes. My Mac has a i5 Intel processor with 8GB RAM and a 8GB Radeon card. Do you think training LORAs will be possible if I increase my RAM or do I need a M1 or a M2 processor from Apple? What is your advice? Thank you in advance.
I was hoping someone with more hardware knowledge would answer..., My guess is the older architecture will not be able to handle the GPU requirements, without the new fancy Apple Silicone 'unified' memory. I still recommend DreamLook.ai for training, it is fast and a lot cheaper than a new Macbook...
That happened to me too. The app crashed on my iPhone and iPad as soon as I started training. I then switched to my MacBook M2 and the training went through
Absolute greatThank you! I wouldn't even know that it was possible without your tutorial. Looking forward to more.
Thank you for your video. It helped me train my first LoRA model.
Thank you so much! I just did my first Lora using Draw Things. Your tutorial was really helpful.
Hi, thank you for this tutorial and all your content. Could i use vertical and horizontal different resolutions?, for example, 384 x 576 px (for portrait images)
I have only ever trained with square images... I have heard that people do use different ratio images while training, but I think all the pics need to be same ratio.... I think the trick is to continue training by adding more steps with all new images - but again, I have not tried it.
I can't get the face to be the same, it is similar yes, but it is not the same, I used 30 images, I will continue adding more
One thing I don't understand is how you create all of that images with the same face
Just a question, how do you prepare your images? Resizing , cropping, sharpening etc
I get best results from head/face shots (include eyebrows to top of shoulders) different angles, expressions, and lighting/environment. My pics are cropped square 2048x2048, rendered from 3D software.
Thanks for the insight! Attempting to make a LORA of my dog.
Looks amazing! What do you mean by overcooked and how are you checking this? Do you have a video explaining this?
Thanks,
There’s hardly any info about Draw Things. So everything you post is really a valuable resource.
How many images do you use for the training? Or what do you say is the minimum or maximum that makes sense.
Also, would you suggest training of 1.5 Lora for people with only 16 GB of ram or use SDXL with 512 x 512?
Thanks for the great content.
I think you can do 512x512 XL on 16GB, but it will be slow because the memory will sometimes need to swap to the hdd. Shut down all other apps, especially web and Discord.
number of pics is maybe between 5 and 25 (mine was 27 here), more pics will increase RAM so use your best images.
Excellent work & gracias!
Absolute great tutorial! Thank you!
sweeet, thanks
Outstanding series!!
Is that your character's voice?
yeah, for now...
My training is complete but how do I get to my Lora?
they are automatically added to your LoRA list. Search for them by name.
you helped me
Thanks for the video. Is it possible to add more photos to the training (to improve model) after training is finished?
I think so, just reload the LoRA by name and the settings should fill-in as before. Then you can change the photos and set the training steps higher to resume...
But also consider it might be easier to start a new training session and create multiple LoRA - rather than over-training a model you like with extra garbage.
I can’t find the “Lora manager”... can you please provide more information?
Click on the LoRA dropdown selector... the top item is 'Disable', the 2nd item is 'Manage...'
How did you write/use your image generation script?
I had to add each LoRA by name in the script... I didn't figure out a way to load each automatically, unfortunately
Thank you for the really helpful tutorial. I tried to train my own LORA with 12 photos and managed to get the captions, but every time I start the training the program crashes. My Mac has a i5 Intel processor with 8GB RAM and a 8GB Radeon card. Do you think training LORAs will be possible if I increase my RAM or do I need a M1 or a M2 processor from Apple? What is your advice? Thank you in advance.
I was hoping someone with more hardware knowledge would answer..., My guess is the older architecture will not be able to handle the GPU requirements, without the new fancy Apple Silicone 'unified' memory.
I still recommend DreamLook.ai for training, it is fast and a lot cheaper than a new Macbook...
@@CutsceneArtist I fear you are right. After upgrading my Mac to 64GB RAM the program still crashes when it comes to the training. Sad...
How to hide text between settings?
click on the Name of the setting to hide the small white text
Every time I tried to train some images the app crashes, I'm using an iPad, also I would like to know how long is the wait for training a model
That happened to me too. The app crashed on my iPhone and iPad as soon as I started training. I then switched to my MacBook M2 and the training went through