Full Training Tutorial and Guide and Research For a FLUX Style
•
4
Furkan Gözükara
MonsterMMORPG
AI & ML interests
Check out my youtube page SECourses for Stable Diffusion tutorials. They will help you tremendously in every topic
Articles
Organizations
Posts
38
Post
3433
Huge news for Kohya GUI - Now you can fully Fine Tune / DreamBooth FLUX Dev with as low as 6 GB GPUs without any quality loss compared to 48 GB GPUs - Moreover, Fine Tuning yields better results than any LoRA training could
Config Files
I published all configs here : https://www.patreon.com/posts/112099700
Tutorials
Fine tuning tutorial in production
Windows FLUX LoRA training (fine tuning is same just config changes) : https://youtu.be/nySGu12Y05k
Cloud FLUX LoRA training (RunPod and Massed Compute ultra cheap) : https://youtu.be/-uhL2nW7Ddw
LoRA Extraction
The checkpoint sizes are 23.8 GB but you can extract LoRA with almost no loss quality - I made a research and public article / guide for this as well
LoRA extraction guide from Fine Tuned checkpoint is here : https://www.patreon.com/posts/112335162
Info
This is just mind blowing. The recent improvements Kohya made for block swapping is just amazing.
Speeds are also amazing that you can see in image 2 - of course those values are based on my researched config and tested on RTX A6000 - same speed as almost RTX 3090
Also all trainings experiments are made at 1024x1024px. If you use lower resolution it will be lesser VRAM + faster speed
The VRAM usages would change according to your own configuration - likely speed as well
Moreover, Fine Tuning / DreamBooth yields better results than any LoRA could
Installers
1-Kohya GUI accurate branch and Windows Torch 2.5 Installers and test prompts shared here : https://www.patreon.com/posts/110879657
The link of Kohya GUI with accurate branch : https://github.com/bmaltais/kohya_ss/tree/sd3-flux.1
Config Files
I published all configs here : https://www.patreon.com/posts/112099700
Tutorials
Fine tuning tutorial in production
Windows FLUX LoRA training (fine tuning is same just config changes) : https://youtu.be/nySGu12Y05k
Cloud FLUX LoRA training (RunPod and Massed Compute ultra cheap) : https://youtu.be/-uhL2nW7Ddw
LoRA Extraction
The checkpoint sizes are 23.8 GB but you can extract LoRA with almost no loss quality - I made a research and public article / guide for this as well
LoRA extraction guide from Fine Tuned checkpoint is here : https://www.patreon.com/posts/112335162
Info
This is just mind blowing. The recent improvements Kohya made for block swapping is just amazing.
Speeds are also amazing that you can see in image 2 - of course those values are based on my researched config and tested on RTX A6000 - same speed as almost RTX 3090
Also all trainings experiments are made at 1024x1024px. If you use lower resolution it will be lesser VRAM + faster speed
The VRAM usages would change according to your own configuration - likely speed as well
Moreover, Fine Tuning / DreamBooth yields better results than any LoRA could
Installers
1-Kohya GUI accurate branch and Windows Torch 2.5 Installers and test prompts shared here : https://www.patreon.com/posts/110879657
The link of Kohya GUI with accurate branch : https://github.com/bmaltais/kohya_ss/tree/sd3-flux.1
Post
2814
Detailed Comparison of JoyCaption Alpha One vs JoyCaption Pre-Alpha — 10 Different Style Amazing Images — I think JoyCaption Alpha One is the very best image captioning model at the moment for model training — Works very fast and requires as low as 8.5 GB VRAM
Where To Download And Install
You can download our APP from here : https://www.patreon.com/posts/110613301
1-Click to install on Windows, RunPod and Massed Compute
Official APP is here where you can try : fancyfeast/joy-caption-alpha-one
Have The Following Features
Auto downloads meta-llama/Meta-Llama-3.1–8B into your Hugging Face cache folder and other necessary models into the installation folder
Use 4-bit quantization — Uses 8.5 GB VRAM Total
Overwrite existing caption file
Append new caption to existing caption
Remove newlines from generated captions
Cut off at last complete sentence
Discard repeating sentences
Don’t save processed image
Caption Prefix
Caption Suffix
Custom System Prompt (Optional)
Input Folder for Batch Processing
Output Folder for Batch Processing (Optional)
Fully supported Multi GPU captioning — GPU IDs (comma-separated, e.g., 0,1,2)
Batch Size — Batch captioning
Where To Download And Install
You can download our APP from here : https://www.patreon.com/posts/110613301
1-Click to install on Windows, RunPod and Massed Compute
Official APP is here where you can try : fancyfeast/joy-caption-alpha-one
Have The Following Features
Auto downloads meta-llama/Meta-Llama-3.1–8B into your Hugging Face cache folder and other necessary models into the installation folder
Use 4-bit quantization — Uses 8.5 GB VRAM Total
Overwrite existing caption file
Append new caption to existing caption
Remove newlines from generated captions
Cut off at last complete sentence
Discard repeating sentences
Don’t save processed image
Caption Prefix
Caption Suffix
Custom System Prompt (Optional)
Input Folder for Batch Processing
Output Folder for Batch Processing (Optional)
Fully supported Multi GPU captioning — GPU IDs (comma-separated, e.g., 0,1,2)
Batch Size — Batch captioning
models
64
MonsterMMORPG/Best_FLUX_Fine_Tunings_Comparisons
Updated
MonsterMMORPG/Big_FLUX_Fine_Tuning_Experiments
Updated
•
1
MonsterMMORPG/256_Imgs_FLUX_Fine_Tuning_Trainings_Best
Updated
MonsterMMORPG/Generative-AI
Updated
•
3
MonsterMMORPG/SECourses_SUPIR
Updated
•
982
MonsterMMORPG/temp29
Updated
MonsterMMORPG/Patreon_SECourses_ROCKs
Updated
MonsterMMORPG/SECourses_Patreon_Rocks
Updated
MonsterMMORPG/CapFiles
Updated
MonsterMMORPG/mich
Updated