Model reference · open weights
Flex.1-alpha is an open-weight image model from ostris. Flex.1-alpha (BF16) weighs 26.3 GB; the smallest configuration that runs it is RTX 4090 24 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the ostris/Flex.1-alpha model card, 2026-10-01
What it is
| Released by | ostris |
|---|---|
| Released | 2025-01-18 |
| Parameters | 8.2B |
| VRAM | 26.3 GB for the weights |
What it runs on
| Card | One image | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 4060 Ti 16 GB | does not fit | |
| RTX 3090 24 GB | tight (encoders offloaded) | 23.4 GB |
| RTX 4090 24 GB | tight (encoders offloaded) | 23.4 GB |
| RTX 5090 32 GB | fits (encoders offloaded) | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
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 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.
I am just a solo Machine Learning Engineer doing this in my free time with my own money because I truly believe in open source models. I have already spent a significant amount of time and money to get this model to where it is. But to get this model where I want it to be, I need to continue to dump a significant amount of time and money into it, well beyond what I am financially capable of doing on my own. I have set up a Patreon for those individuals and organizations that want to financially support this project. I plan to also allow support in other ways soon for those that prefer to get their hands dirty.
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.)
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.
More detailed instructions coming soon.
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, 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.
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.
Day 1 LoRA training support is in AI-Toolkit. You can use the example config to get started.
A special thanks to the following people/organizations, but also the entire ML community and countless researchers.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel and load the workflow from the model's card on Hugging Face; choose this model's file in its loader.
# on your rented machine: pip install diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained("ostris/Flex.1-alpha", torch_dtype=torch.bfloat16).to("cuda")
image = pipe(prompt="a red bicycle on a cobbled street").images[0]
image.save("/workspace/out.png")# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the model (20.2 GB)
get ostris/Flex.1-alpha Flex.1-alpha.safetensors diffusion_models
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST, PORT and BOOKING are your machine's, from its page in the console
ssh -o HostKeyAlias=axforge-BOOKING -o StrictHostKeyChecking=accept-new -L 8188:localhost:8188 dev@HOST -p PORT