when i run the code in this vedio .cmd show this to me. is that means i dont run on the GPU?
when i run the code in this vedio .cmd show this to me. is that means i dont run on the GPU?
生YouTubeSECourses
Databricks’ #Dolly v2 is a free, open source, commercially useable ChatGPT-style #AI model. Dolly 2.0 could spark a new wave of fully open source LLMs similar to #ChatGPT . Open source community working hardest to bring up a model that can compete with GPT4. Our discord: https://bit.ly/SECoursesDiscord
If I have been of assistance to you and yo...
If I have been of assistance to you and yo...
生
生i look my Task Manager my ram is increasing so high but gpu not increase
Fdo you need regularization images for training a photograph style lora from movie references?
or is there a good tutorial specifically for this?
its unclear when you need to tag the images, (or remove stuff from tags) when you need regularization images, when it comes to training a photographic style vs a character vs a pose/action vs details applied to any of the above, is there good info about this anywhere? (info seems to change every 2 weeks lol)
or a loha/lycoris if they are better
never tried to train one
or is there a good tutorial specifically for this?
its unclear when you need to tag the images, (or remove stuff from tags) when you need regularization images, when it comes to training a photographic style vs a character vs a pose/action vs details applied to any of the above, is there good info about this anywhere? (info seems to change every 2 weeks lol)
or a loha/lycoris if they are better
never tried to train one
Flike a table that says:
training photoreal faces? dont need regularisation images, here's good starter settings
training a photographic style, dont do this, these settings are good, etc, would be amazing
training photoreal faces? dont need regularisation images, here's good starter settings
training a photographic style, dont do this, these settings are good, etc, would be amazing
Fthat could be kept updated
Θare these good settings for dreambooth
Θalso for training people is it best to use LoRa or Dreambooth training?
Θso for the best resultst possible
Θsize doesnt matter for me
ADr. Furkan Gözükara told me that Dreambooth is the best for training people. I haven't actually tried LoRA yet, but Textual Inversion produced terrible results. Dreambooth produces great results.
ΘOk so good choice i chose dreambooth
ΘThank you very much for your repsonse
Ftorch version or optimizations could be. i am planning an optimizations tutorial
Fwhat do you see on cmd_?
Fyou can try reinstall with different commit
Fye looks like it didnt use your gpu. what gpu do you have?
Fclass images improve quality but not mandatory. you dont need to tag them
Fi find Dreambooth better
Khow to create good regularization images for other things like woman , animal etc like https://www.patreon.com/posts/realistic-vision-82085317
Ki think it is for 30/40 series nvidia gpus , i am training with bf16 on rtx4080 laptop gpu and it works
生3060ti vram 8g and ram 16g
Fwhat could be happening if my training set is overcooked at 90 steps per image using 25 class images per training img?
F0.000001 LR
Fi'm using 57 images
Fthey shouldn't be overcooked that soon
Fwell best way is generating images on the model you want
Fthen delete the outliers
Fbecause usually these models are extremely overtained and biased
Ffor example i deleted naked pictures it generates
Fthat one supports bf16
F57 images are for a person?
生sorry i not really know supports bf16 it means i cant test it?
F3060ti supports you can test
Fboth bf16 and fp16
生oh but when i trigger this on the new question happen
生
生
Fyes
Fi've been training with 50-60 images per person and it works fine
Fat least in the past
Fi think you need smaller model
F12b wont work on 12gb
生i use 7b model now it say this
生
Flooks like installation error
Fyou can try this
Factivate venv
Fpip uninstall torch
Fpip uninstall torchvision