Pierre-Louis Braun's picture

4 3

Pierre-Louis Braun

alkeryn

·

alkeryn

AI & ML interests

None yet

Recent Activity

liked a model 1 day ago

fishaudio/fish-agent-v0.1-3b

Reacted to MonsterMMORPG's post with 🔥 about 2 months ago

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

View all activity

Organizations

None yet

alkeryn's activity

New activity in Weyaxi/2x-LoRA-Assemble-13B about 1 year ago

possible reason it might work

#1 opened about 1 year ago by

New activity in TheBloke/Nous-Hermes-13B-GGML over 1 year ago

Uh oh, the "q's"...

#2 opened over 1 year ago by

New activity in kaiokendev/superhot-13b-16k-no-rlhf-test over 1 year ago

Difference between this and 8k version?

#1 opened over 1 year ago by

New activity in CompVis/stable-diffusion-v-1-4-original about 2 years ago

Difference between the Model weights

#7 opened about 2 years ago by