OK thank you i will test it 🌹
OK 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
Calso comfi.ui?
Fnot yet but will do hopefully
Fso many stuff recently
PIs anyone online?
Fyes
Dhttps://huggingface.co/spaces/HumanAIGC/OutfitAnyone This shows much promise impressive
Every interesting. Is it stable diffusion based? The fact that they only allow the preset model images to be put in there makes me think there is a pre-prepared controlnet going on but it is very smooth none the less. Thanks for sharing.
Sim from NJ. what exactly you need?
Cdid you test it? What was your result? 
JHey Everyone today I am recently sharing my new updated blog post please check and share your feedback.
https://jillanisofttech.medium.com/redefining-excellence-in-mlops-a-guide-to-optimal-machine-learning-experimentation-environments-0c4ab61905d1
ai
https://jillanisofttech.medium.com/redefining-excellence-in-mlops-a-guide-to-optimal-machine-learning-experimentation-environments-0c4ab61905d1
ai
Medium
By 
Muhammad Ghulam Jillani(Jillani SoftTech), Senior Data Scientist and Machine Learning Engineer
Muhammad Ghulam Jillani(Jillani SoftTech), Senior Data Scientist and Machine Learning EngineerEHey everyone! After doing a lot of work in the generative AI space I want to start investing in training an LLM to process input - like a chatbot as an example
EAny good videos/articles on how to train my own?
Fthis is a good topic. sadly i couldnt find time yet
Ewill report back, i did find this which claims to be the automatic 1111 UI for text models: https://github.com/oobabooga/text-generation-webui
GitHub
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models. - GitHub - oobabooga/text-generation-webui: A Gradio web UI for Large Language Mod...
KHello, I want to replace my AMD graphics card with an Nvidia graphics card for stable diffusion. I wanted to buy a 3080, but since my PSU is 600W, the healthiest and newest generation card I can go for is RTX 4060, but with 8GB VRAM, I'm not sure if it's sufficient for stable diffusion. Therefore, I'm torn between 3060 12GB and 4060 due to VRAM, as I don't have any other alternatives due to my PSU
Ftry to go as much as possible VRAM
Fif your 600 watt is real
Fyou can go with RTX 3090 too
Fat worst you can do some undervoltage
KI consulted with my friend, and he also advised me to upgrade to a 3080 and change the PSU later, which didn't seem unreasonable. However, I'm concerned about the inadequacy of the PSU causing damage to other components in the system.
Fi think it would just shut down pc
KEveryone I asked recommended getting the 3080, and if you also approve, then it would be best for me to go with the 3080
Fhow much vram it has?
K10gb
Fi would buy RTX 4060 - 16 GB
Fmuch better
Flook for it
KI can't buy anything within my budget except 3080
Fi see
Fmaybe used card?
SWhat video card do you have now? I have AMD RX 6800XT 16gb and it handles Lora's training and stable diffusion quite well. The only inconvenience is that I had to install Ubuntu 20.04 on a second disk in order to have hardware acceleration