A year ago, when I was building the sampling mechanism for ai-toolkit, I accidentally left my name (Jaret) hard coded as the trigger word, buried deep in the code. It really freaked me out and made me question reality when my name started showing up in all the training samples.

folks are training some incredibly creative Flux Loras in our discord, it’s super fun to watch these lil models “grow up” - come join and apply for a Loradex trainer pass for free high end lora training - links below

This is absolutely amazing!

New training best practice, random case dropout.

I absolutely love working at glif and you would too.

Does anyone know of / have a script to convert a diffusers flux checkpoint to the original format?

I haven't spoken much about my ongoing project to de-distill schnell to make a permissive licensed version of flux, but I have been updating it periodically as it trains. I just noticed it is the #2 trending text-to-image model on Hugging Face. Working on aesthetic tuning now.

Almost every VLM captions like : "The image appears to possibly feature a man who could be in a mood some would describe as happy" vs how people prompt "A happy man". And they all seem to ignore my instructions do it otherwise.

Toying with an idea of a living community model for the next step for open flux. Allow the community to fine-tune the model on their own datasets and target identified weak spots using set training configs. Then, once a week/month, all of these are merged into the base model.

I am honestly pretty happy with how OpenFLUX is turning out. I never expected to actually get it to where it is currently, and it still has a long way to go before it is where I want it to be.

I'm still off and on cooking a version of SD1.5 that has a 16ch VAE and T5XL text encoder. It takes forever to learn the fine detail since it is 4x the amount of data in a 16ch VAE. It is frustrating because it is so close, yet still so far.