SmilingWolf/wd-eva02-large-tagger-v3
Updated
β’
16.7k
β’
72
PyHornet
pyhornet
AI & ML interests
Hello.
Recent Activity
liked
a model
9 days ago
SmilingWolf/wd-eva02-large-tagger-v3
liked
a model
9 days ago
Akumetsu971/SD_Anime_Futuristic_Armor
liked
a Space
10 days ago
finegrain/finegrain-image-enhancer
Organizations
None yet
pyhornet's activity
liked
2
models
9 days ago
liked
a
Space
10 days ago
reacted to
dylanebert's
post with π
16 days ago
Post
2650
blender has AI now
reacted to
nroggendorff's
post with π€―
19 days ago
Post
1844
uhh..
- 11 replies
liked
a
Space
19 days ago
liked
a
Space
28 days ago
liked
a
Space
about 1 month ago
Question
3
#33 opened about 1 month ago
by
zelk12
π© Report: Stuck in queue
2
#32 opened about 1 month ago
by
pyhornet
liked
2
Spaces
about 1 month ago
liked
2
Spaces
about 2 months ago
reacted to
MonsterMMORPG's
post with π
about 2 months ago
Post
4105
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