diff --git a/.gitattributes b/.gitattributes index f0b2671..bbc871b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text assets/banner_0_0_6.png filter=lfs diff=lfs merge=lfs -text +assets/banner_0_0_8.png filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index b389f69..e21fc52 100644 --- a/README.md +++ b/README.md @@ -4,25 +4,16 @@ library_name: diffusers pipeline_tag: text-to-image --- - +
# Not Ready -This is a WIP and not ready for use. This is an early testing version for research and development. You may know what this is and how to use it, if so, -feel free, but it will change as I continue to develop it. I plan to do many updates to it frequently. So you may want to set a revision if you intend to use it anyway. +This is a WIP. It is nearing a state I am going to call "early pre alpha". You are welcome to start messing with it at this point, but it still has a ways to go before it is ready for people to start finetuning on it. New updates are being pushed every few days as it continues to train. I will update this message when it is ready for that.
## What is this? -[FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) is an amazing distilled model with an apache 2.0 license. However, it is not finetunable. LoRAs, IP adapters, control nets, etc, cannot be trained on it -because it is distilled. The goal of this project is to finetune a non-distilled version of it that can be used as a training base to train adapters for FLUX.1-schnell. - -## Current Issues - -Since we are breaking the distillation, this model will need many steps and guidance to produce good results. Currently, this model, like the schnell version, does not -have guidance embeddings. Because of this (and possible other factors) images generated with this model will not look great. However, this hopefully will not affect training, -since guidance is not used during training. The things trained on this model are intended to be used on the schnell version anyway. I am working on training guidance -embeddings for it, but hopefully it will work as a training base without them. +This project started as a way to train adapters for the [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) model. But has evolved over time. The purpose of this project now, is to create an open source version of FLUX.1 that uses classic CFG and is finetunable for the community. Since it requires CFG, it will require a different pipeline than the original FLUX.1. This pipeline can be found in open_flux_pipeline.py in this repo. diff --git a/assets/banner_0_0_8.png b/assets/banner_0_0_8.png new file mode 100644 index 0000000..35725bf --- /dev/null +++ b/assets/banner_0_0_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2688b666acc4a469f5262b305b766085b5030fb3e9645ded26d997db755ac13d +size 1039464 diff --git a/transformer/diffusion_pytorch_model-00001-of-00003.safetensors b/transformer/diffusion_pytorch_model-00001-of-00003.safetensors index 2ed5014..a03aa40 100644 --- a/transformer/diffusion_pytorch_model-00001-of-00003.safetensors +++ b/transformer/diffusion_pytorch_model-00001-of-00003.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fd648c3cb141747a95d4a98581cdad8915f35686a680d240c9dd80372c08961f +oid sha256:727c63dfa6394872131300e240b942daefd078ba78b163f3b8304b75b391e2e3 size 9962580296 diff --git a/transformer/diffusion_pytorch_model-00002-of-00003.safetensors b/transformer/diffusion_pytorch_model-00002-of-00003.safetensors index 9ffbe3c..f16e7aa 100644 --- a/transformer/diffusion_pytorch_model-00002-of-00003.safetensors +++ b/transformer/diffusion_pytorch_model-00002-of-00003.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bb9ea505f18b34becdbb7f90308bfbacba2afffe754680fd3d6bf72daf23a268 +oid sha256:43501ab821ef7643a8caf4f7b2c5063b912181fc540e38855a76d7739b3cf835 size 9949328904 diff --git a/transformer/diffusion_pytorch_model-00003-of-00003.safetensors b/transformer/diffusion_pytorch_model-00003-of-00003.safetensors index f6f9bd0..8476708 100644 --- a/transformer/diffusion_pytorch_model-00003-of-00003.safetensors +++ b/transformer/diffusion_pytorch_model-00003-of-00003.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b0cb033b006957106248cbdba4eab21187184e8b029f9223dc6b0cd502492831 +oid sha256:a090e5a8efea7801c3f28a8fb6838fce0031d475d6f0eb8c2a4e8b9bfb9f9660 size 3870584832