FLUX.1-dev#
FLUX.1-dev is a 12B parameter text-to-image diffusion transformer from Black Forest Labs, trained with flow matching. It produces high-fidelity images and is designed for non-commercial research and development use.
Task |
Text-to-Image |
Architecture |
DiT (Flow Matching) |
Parameters |
12B |
HF Org |
Available Models#
FLUX.1-dev: 12B parameters
Task#
Text-to-Image (T2I)
Example HF Models#
Model |
HF ID |
|---|---|
FLUX.1-dev |
Example Recipes#
Recipe |
Description |
|---|---|
Fine-tune — FLUX.1-dev with flow matching |
|
Pretrain — FLUX.1-dev with flow matching |
Try with NeMo AutoModel#
1. Install (full instructions):
pip install nemo-automodel
2. Clone the repo to get the example recipes:
git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel
3. Run the recipe from inside the repo:
torchrun --nproc-per-node=8 \
examples/diffusion/finetune/finetune.py \
-c examples/diffusion/finetune/flux_t2i_flow.yaml
Run with Docker
1. Pull the container and mount a checkpoint directory:
docker run --gpus all -it --rm \
--shm-size=8g \
-v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
nvcr.io/nvidia/nemo-automodel:26.02.00
2. Navigate to the AutoModel directory (where the recipes are):
cd /opt/Automodel
3. Run the recipe:
torchrun --nproc-per-node=8 \
examples/diffusion/finetune/finetune.py \
-c examples/diffusion/finetune/flux_t2i_flow.yaml
See the Installation Guide and Diffusion Fine-Tuning Guide.
Training#
See the Diffusion Training and Fine-Tuning Guide and Dataset Preparation.