Kohya brought massive improvements to FLUX LoRA (as low as 4 GB GPUs) and DreamBooth / Fine-Tuning (as low as 6 GB GPUs) training
Furkan G?zükara
PhD. Computer Engineer. Produces Content For FLUX, LoRA, Fine Tuning, Stable Diffusion, SDXL, Training, DreamBooth Training, Deep Fake, Voice Cloning, Text To Speech, Text To Image, Text To Video, Generative AI, LLMs
You can download all configs and full instructions
> https://www.patreon.com/posts/112099700 - Fine Tuning post
> https://www.patreon.com/posts/110879657 - LoRA post
Kohya brought massive improvements to FLUX LoRA and DreamBooth / Fine-Tuning (min 6GB GPU) training.
Now as low as 4GB GPUs can train FLUX LoRA with decent quality and 24GB and below GPUs got a huge speed boost when doing Full DreamBooth / Fine-Tuning training
You need minimum 4GB GPU to do a FLUX LoRA training and minimum 6 GB GPU to do FLUX DreamBooth / Full Fine-Tuning training. It is just mind blowing.
You can download all configs and full instructions > https://www.patreon.com/posts/112099700
The above post also has 1-click installers and downloaders for Windows, RunPod and Massed Compute
The model downloader scripts also updated and downloading 30+GB models takes total 1 minute on Massed Compute
You can read the recent updates here : https://github.com/kohya-ss/sd-scripts/tree/sd3?tab=readme-ov-file#recent-updates
This is the Kohya GUI branch : https://github.com/bmaltais/kohya_ss/tree/sd3-flux.1
Key thing to reduce VRAM usage is using block swap
Kohya implemented the logic of OneTrainer to improve block swapping speed significantly and now it is supported for LoRAs as well
Now you can do FP16 training with LoRAs on 24 GB and below GPUs
Now you can train a FLUX LoRA on a 4 GB GPU - key is FP8, block swap and using certain layers training (remember single layer LoRA training)
It took me more than 1 day to test all newer configs, their VRAM demands, their relative step speeds and prepare the configs :)
Motion Designer, GenAI Researcher
3 个月Ey Furkan, you usually say you train all images at 1024x1024, do you have any research or post supporting this premise? Thank you
Creative Technologist - AI Pragmatist
3 个月VRAM improvements to FLUX LoRA look amazing, Do you think these improvements will make it more approachable by lower end users? Thanks so much for sharing. It looks like it was a ton of work!