ok, im doing clean install
ok, im doing clean install
Fgreat let me know
Fyou have python 3.10 righyt?
Jyes, 3.10.11 as u said it's the best right now 
J@Furkan Gözükara SECourses Ok, this error after installation 1024_8bit "Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit the quantized model. If you want to dispatch the model on the CPU or the disk while keeping these modules in 32-bit, you need to set
load_in_8bit_fp32_cpu_offload=Truedevice_mapfrom_pretrainedye give it a try but 6gb really low
Jyes, i know :/ i should think about sth with more vram
MI have AudioCraft Plus. How can I generate music with a beginning ("intro") and an end?
Fgood question
Fsadly i dont know if that possible
Fit has input audio but not input and ending as far as i know
MBecause the Stable Audio sample has a beginning and an end, and I've also generated music in Wondershare Filmora and it's been solved there, so I'm wondering which other music generators are suitable for that, and I'd like to run it on my home computer.
DYouTubeFull-stack Dev Mastery
Learn how to build a full application with ChatGPT
#ai #chatgpt #backend #frontend #fullstack #webdesign #webdev #webdevelopment #html #css #js #javascript #react #angular #react #reactjs #artificialintelligence #chatgpt4
#ai #chatgpt #backend #frontend #fullstack #webdesign #webdev #webdevelopment #html #css #js #javascript #react #angular #react #reactjs #artificialintelligence #chatgpt4
TT7950x3d+4090+64gb ddr5 .. for SDXL i use your config dreambooth 24GB_NoTextEncoder , with 60 Training images my face 40 repeats ,your Regularisation images 1024x1024_2734_imgs 1 Repeats .....9 hours of training and good result of high quality , kohya-ss v22.4.1 without any error messages
T1.5 Based Models Training Config me_sd_7e7_v2.json same 60 Training images of my face 768x768 ,40 repeats and Regularisation images man_5200_imgs_768x768 1 Repeats = 5 hours of bad result getting all same picture
Twhat im doing wrong ?
F60 train 40 repeat
Fhow many epochs?
Fit makes 4800 steps with reg images
Fif 1 epoch
T8 , i didnt change anything just put the images folders
Fok 8 is too many
Fwhat is your speed how many second / it
T1.25
Fthat is normal speed
Fso you need to reduce number of epochs
Fi suggest this
F100 repeat
F1 epoch
Fand save checkpoints
F100 * 60 *2 = 12000 steps
Fso save every 1201 steps
Fto see which one will perform best
TOK thank you i will test it 
Ttrain unet: True, text_encoder1: False, text_encoder2: False
number of models: 1
number of trainable parameters: 2567463684
prepare optimizer, data loader etc.
use Adafactor optimizer | {'scale_parameter': False, 'relative_step': False, 'warmup_init': False, 'weight_decay': 0.01}
constant_with_warmup will be good / スケジューラはconstant_with_warmupが良いかもしれません
enable full bf16 training.
running training / 学習開始
num examples / サンプル数: 6000
num batches per epoch / 1epochのバッチ数: 12000
num epochs / epoch数: 1
batch size per device / バッチサイズ: 1
gradient accumulation steps / 勾配を合計するステップ数 = 1
total optimization steps / 学習ステップ数: 12000
steps: 0%| | 0/12000 [00:00<?, ?it/s]
epoch 1/1
steps: 3%|█▊ | 416/12000 [07:49<3:38:06, 1.13s/it, avr_loss=0.105]
number of models: 1
number of trainable parameters: 2567463684
prepare optimizer, data loader etc.
use Adafactor optimizer | {'scale_parameter': False, 'relative_step': False, 'warmup_init': False, 'weight_decay': 0.01}
constant_with_warmup will be good / スケジューラはconstant_with_warmupが良いかもしれません
enable full bf16 training.
running training / 学習開始
num examples / サンプル数: 6000
num batches per epoch / 1epochのバッチ数: 12000
num epochs / epoch数: 1
batch size per device / バッチサイズ: 1
gradient accumulation steps / 勾配を合計するステップ数 = 1
total optimization steps / 学習ステップ数: 12000
steps: 0%| | 0/12000 [00:00<?, ?it/s]
epoch 1/1
steps: 3%|█▊ | 416/12000 [07:49<3:38:06, 1.13s/it, avr_loss=0.105]
T100% gpu utilization ,dedicated gpu memory 17.2/24.0 GB , 20.6 gb ram in use
Ti turn off Gradient checkpointing ,
Tsteps: 0%| | 20/12000 [06:13<62:08:29, 18.67s/it, avr_loss=0.129]
Fit starts using shared VRAM
Ftherefore it will become too slow
FOneTrainer is fitting into 24 GB so it brings speed up there
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=40)
DGitHub
Contribute to chaojie/ComfyUI-Moore-AnimateAnyone development by creating an account on GitHub.
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=16)
Fthanks
BI want to create a space on my mac where i can install and run packages and experiment around but I should be able to delete this space/folder and after that none of what i did or installed during my experimentation should remain on my pc. how can I do this?
Fsadly i dont know mac. but best would be installing a windows or linux on mac if possible
Bdoes docker do this kind of thing
Fare you able to run dockers on mac?
Fyes it would do
Fbut it is important if docker will be able to use your bare metal hardware
C@Furkan Gözükara SECourses have you done a tutorial on stable video diffusion
