FLUX.1 is a new open-source image generation model developed by Black Forest Labs, the creators of Stable Diffusion. It's available on Replicate today, and you can run it in the cloud with one line of code.
Here's an example of how to run FLUX.1 on Replicate using JavaScript:
You can try out FLUX.1 right in your browser, or run it programmatically in your language of choice.
FLUX.1 models have state-of-the-art performance in prompt following, visual quality, image detail, and output diversity. Here are some particular areas where we've been impressed:
Text! Unlike older models that often messed up similar-looking letters, Flux can handle tricky words with repeated letters. This makes it great for designs where text needs to be accurate. Check out this Black Forest Flux Schnell gateau:
Complex composition. Flux is amazing at following complex instructions about where things should go in an image. For example, given the prompt "Three magical wizards standing on a yellow table, each holding a sign. On the left, a wizard in black robes holds a sign that says 'AI'; in the middle, a witch in red robes holds a sign that says 'is'; and on the right, a wizard in blue robes holds a sign that says 'cool'", Flux creates this scene perfectly:
Hands that (mostly) look right. Hands are tough for AIs, but Flux does a pretty good job. You'll usually get the right number of fingers in the right places. It's not perfect, but it's a big step up—it's consistently better than any other open text-to-image model we've tried:
FLUX.1 comes in three variants:
FLUX.1 is priced per image:
FLUX.1 is a fantastic model, so do try it out. And keep watching this space—now that the model is out in the wild, we are starting to work on features like fine-tuning for FLUX.1, so stay tuned.