From what I read ldsr was working and now it's not.
From what I read ldsr was working and now it's not.
Fjust download the model file
FYouTubeSECourses
Our Discord : https://discord.gg/HbqgGaZVmr. How to use custom, different, .safetensors and SD 2.1 on Automatic1111 Web UI. 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 Go...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Go...
Fye that is sufficient. i will test for you on my computer
PThanks
Fsorry for delay
Fi just tested and it works
Fdo you need lsdr model file?
F
HCan you run stable diffusion on amd gpus?
HIs there an alternative to cuda?
Fnmkd gui supports it
HYou are a extremely wonderful engineer
Han* 
KHi Dr.Furkan and everyone, is there any way to save checkpoint only after 80 epochs are completed? I want to save a checkpoint every 10 epochs like 80-90-100-110... but instead it saves 10-20-30-40... and takes too much spaces. Thank you very much.
DI don't think so, atleast in A1111... maybe we would need to write a custom script for that, should be fairly easy.
KThank you. My current workaround is to train it until 80 epochs without saving >> get 1 checkpoint >> keep training that checkpoint until 150 epochs and save every 10 so I get 90-100-110...
Mthat’s the way to do it.
Fthank you so much fıor compliments
Fyes you can do that
Fwhat are you using to do training google colab?
YHere come some more. Fantastic work!
YIm following your video "Best training setup parameters for Dreambooth using classificaiton images.
YI have prepared a folder with handpicked classification images, but when I start training dreambooth ignores them and starts creating them. Have you had this problem? Thank you in advance for any help.
Fmust be a configuration error
Fafter saving config click load
Fyou tried that?
Falso show me settings please
YThank you, let me check
Y
YIve tried saving and loading with same issue
Fshow settings please
YWhat is interesting is that it recognizes the classification images it generated on its own, but it wont recognize the ones I put in
Fok use
Fpre processing tool
Fin train tab
Fit will fix
YGreat thanks! Do I have to use a specific ratio for this?
YI intend to use a 960 x 512 when working. On the preprocess images it says 512x512
Fyour classification images probably should be same dimension
Fas your training images
Fif you dont change max resolution they will get downscaled
Ygreat, thanks a lot!
Ykeep up the great work
YIt worked! im so happy!
RHey @Furkan Gözükara SECourses are you aware of any GPT assistants who can already help with captioning datasets. I find myself constantly going back to make changes to a tag word or a string, and have to go back to all the dataset txt files, and it's quite time inefficient. Would imagine being able to leverage GPT + python would bring captioning from an hours to minutes. Any luck yet with applying these GPT agents to captioning?
Fthere are already blip and other captions
Fwith the caption thing what is important is not describing that image
Fthe important thing is which words you want to improve
Fyou want to do fine tuning right?
Dalthough BLIP makes the process much faster, in my opinion it is less accurate. Sometime it produces wrong descriptions for the images. This might affect the training right? I have not tried GPT-4's image description feature yet, but from what I heard, it is quite accurate. maybe a comparison between BLIP and GPT-4 is needed