A Blog post by Black Forest Labs on Hugging Face
Back to Articles
FLUX.2 [klein] is small enough to fine-tune on a single consumer GPU. A LoRA run
on the 4B model fits in 24 GB of VRAM, takes about an hour on an RTX 4090,
and costs roughly $0.50 if you rent the GPU. This guide walks the full loop:
build a dataset, configure the trainer, run it, load the result in
Flux vs SDXL vs SD 1.5: Real Cost-per-Image Across GPUs (2026)
I built a Rust inference engine that streams MoE expert weights from NVMe SSDs, no GPU required
Serving a Fleet of SLMs on One RTX 5080: Multi-Model on a Single Consumer GPU
One of the First Public HiDream-O1-Image LoRAs — and How to Train Your Own
Diffusion Language Models Are Here: Deep Dive into NVIDIA's Nemotron-Labs DLM Architecture
We've made running fine-tunes on Replicate much faster, and the optimizations are open-source.
We've added fine-tuning (LoRA) support to FLUX.1 image generation models. You can train FLUX.1 on your own images with one line…
Create your own fine-tuned Flux model to generate new images of yourself.
FLUX.1 is a new text-to-image model from Black Forest Labs, the creators of Stable Diffusion, that exceeds the capabilities of…
Create and run your own fine-tuned Flux models programmatically using Replicate's HTTP API.
FLUX is now much faster on Replicate, and we’ve made our optimizations open-source so you can see exactly how they work and build…
