Upload folder using huggingface_hub

README.md

@@ -10,7 +10,7 @@ pipeline_tag: text-to-image
 
 ## Description
 
-Flex.1 alpha is a pre-trained base 8 billion parameter rectified flow transformer capable of generating images from text descriptions. It has a similar architecture to FLUX.1-dev, but with fewer double transformer blocks (8 vs 19). It began as a finetune of FLUX.1-schnell which allows us to retain the Apache 2.0 licensing. A guidance embedder has been trained for it so that it no longer requires CFG to generate images.
+Flex.1 alpha is a pre-trained base 8 billion parameter rectified flow transformer capable of generating images from text descriptions. It has a similar architecture to [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev), but with fewer double transformer blocks (8 vs 19). It began as a finetune of [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) which allows the model to retain the Apache 2.0 license. A guidance embedder has been trained for it so that it no longer requires CFG to generate images.
 
 ## Model Specs
 
@@ -19,6 +19,7 @@ Flex.1 alpha is a pre-trained base 8 billion parameter rectified flow transforme
 - True CFG capable
 - Fine tunable
 - OSI compliant license (Apache 2.0)
+- 512 token length input
 
 ## Support Needed
 
@@ -28,9 +29,9 @@ I am just a solo Machine Learning Engineer doing this in my free time with my ow
 
 ## Usage
 
-The model can be used almost identically to FLUX.1-dev and will work out of the box with most inference engines that support that. (Diffusers, ComfyUI etc.) 
+The model can be used almost identically to [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) and will work out of the box with most inference engines that support that. (Diffusers, ComfyUI etc.) 
 
-For ComfyUI, there is an all in one file called `Flex.1-alpha.safetensors`. Put this in your checkpoints folder and use like you would FLUX.1-dev.
+For ComfyUI, there is an all in one file called `Flex.1-alpha.safetensors`. Put this in your checkpoints folder and use like you would [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev).
 
 More detailed instructions coming soon.
 
@@ -38,13 +39,13 @@ More detailed instructions coming soon.
 
 <img src="https://i0.wp.com/ostris.com/wp-content/uploads/2025/01/openflux_is_now_flex1.jpg?resize=1024%2C328&amp;ssl=1" style="max-width: 100%; height: auto;">
 
-Flex.1 started as the FLUX.1-schnell-training-adapter to make training LoRAs on FLUX.1-schnell possible. The original goal was to train a LoRA that can be activated during training to allow for fine tuning on the step compressed model. I merged this adapter into FLUX.1-schnell and continued to train it on images generated by the FLUX.1-schnell model to further break down the compression, without injecting any new data, with the goal of making a stand-alone base model. This became OpenFLUX.1, which was continuously trained for months, resulting in 10 version releases. After the final release of OpenFLUX.1, I began training the model on new data and began experimenting with pruning. I ended up with pruned versions of OpenFLUX.1 that were 7B, and 4B parameters (unreleased). Around this time, flux.1-lite-8B-alpha was released and produced very good results. I decided to follow their pruning strategy and ended up with a 8B parameter version. I continued to train the model for months, adding new datasets and doing various experimental training tricks to improve the quality of the model.
+Flex.1 started as the [FLUX.1-schnell-training-adapter](https://huggingface.co/ostris/FLUX.1-schnell-training-adapter) to make training LoRAs on [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) possible. The original goal was to train a LoRA that can be activated during training to allow for fine tuning on the step compressed model. I merged this adapter into [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) and continued to train it on images generated by the [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) model to further break down the compression, without injecting any new data, with the goal of making a stand-alone base model. This became [OpenFLUX.1](https://huggingface.co/ostris/OpenFLUX.1), which was continuously trained for months, resulting in 10 version releases. After the final release of [OpenFLUX.1](https://huggingface.co/ostris/OpenFLUX.1), I began training the model on new data and began experimenting with pruning. I ended up with pruned versions of [OpenFLUX.1](https://huggingface.co/ostris/OpenFLUX.1) that were 7B, and 4B parameters (unreleased). Around this time, [flux.1-lite-8B-alpha](https://huggingface.co/Freepik/flux.1-lite-8B-alpha) was released and produced very good results. I decided to follow their pruning strategy and ended up with a 8B parameter version. I continued to train the model, adding new datasets and doing various experimental training tricks to improve the quality of the model.
 
-At this point, the model still required CFG in order to generate images. I decided the model needed a guidance embedder similar to FLUX.1-dev, but I wanted it to be bypassable to make the model more flexible and trainable so I trained a new guidance embedder for the model independently of the model weights so that it behaves like an optional adapter leaving the model capable of being trained and inferenced without it.
+At this point, the model still required CFG in order to generate images. I decided the model needed a guidance embedder similar to [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev), but I wanted it to be bypassable to make the model more flexible and trainable so I trained a new guidance embedder for the model independently of the model weights so that it behaves like an optional adapter leaving the model capable of being trained and inferenced without it.
 
 ## Fine Tuning
 
-Flex.1 is designed to be fine tunable. It will finetune very similar to FLUX.1 dev, with the exception of the guidance embedder. With FLUX.1 dev, it is best to fine tune with a guidance of 1. However, With Flex.1, it is best to fine tune with the guidance embedder completely bypassed. 
+Flex.1 is designed to be fine tunable. It will finetune very similar to [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev), with the exception of the guidance embedder. With [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev), it is best to fine tune with a guidance of 1. However, With Flex.1, it is best to fine tune with the guidance embedder completely bypassed. 
 
 Day 1 LoRA training support is in [AI-Toolkit](https://github.com/ostris/ai-toolkit). You can use the [example config](https://github.com/ostris/ai-toolkit/blob/main/config/examples/train_lora_flex_24gb.yaml) to get started.