Today we are happy to release a new trainer designed specifically for high quality portraits: the FLUX Portrait Trainer. The Fal FLUX portrait trainer creates striking portraits, with fine details, bright highlights in the eyes, better representation of different face sizes, better prompt following while maintaining high resemblance. Improved Fine

fal is partnering with recraft.ai to offer the new Recraft V3 (aka red_panda) model. To play around with the new models now, check out the demo page here on fal. Codename "red_panda" – shining in user evaluations The Recraft V3 model, codenamed "red_panda"

fal is partnering with stability.ai to offer the new Stable Diffusion 3.5 Large & Turbo models. To play around with the new models now, check out the demo page here on fal. Where the models shine Stable Diffusion 3.5 stands out as one of the most customizable

FLUX has taken over the image generation space, but getting exactly the style you want can be difficult. This where style LoRAs can help. Training a style LoRA on Fal is easy, but there are some tips and tricks for getting the best results. The Basics: Collecting a Good Dataset

fal is proud to partner with Black Forest Labs to offer both the new FLUX.1.1 [pro] (aka 🫐) and the 2x accelerated FLUX.1 [dev] models. To play around with the new FLUX.1.1 [pro] now, check out the demo page here on fal. Codename "blueberry 🫐"

fal has raised $23M in Seed and Series A funding. The $14M Series A was led by Kindred Ventures with participation from Andreessen Horowitz and First Round Capital and angel investors including Perplexity founder Aravind Srinivas, Vercel founder Guillermo Rauch, Balaji Srinivasan, and Huggingface CTO Julien Chaumond. The Seed round

Flux, the largest SOTA open source text-to-image model to date, developed by Black Forest Labs—the original team behind Stable Diffusion is now available on fal. Flux pushes the boundaries of creativity and performance with an impressive 12B parameters, delivering aesthetics reminiscent of Midjourney. To play around with the model

Today we released the second version of our single step GAN upscaler: AuraSR. We released AuraSR v1 last month and were encouraged by the community response so immediately started training a new version. AuraSR is based on the Adobe Gigagan paper using lucidrain’s implementation as a starting point. The

Open-source AI is in jeopardy. As community interest in AI models skyrocketed over the past year, we noticed that development of new open-source foundational models came to a halt. Some even boldly announced that open-source AI is dead. Not so fast! We are excited to present you the first release

Today we are releasing AuraSR, a 600M parameter upsampler model derived from the GigaGAN paper. This model can upscale low-res images to 4x the resolution, and can be applied repeatedly. We are publishing this model under a truly open source license. AuraSR excels in upscaling images generated by text-to-image models.

Greetings friends of fal! At fal, we are building the fastest and most reliable inference cloud for generative AI. We are thrilled to announce some major updates. Here’s what’s new: Stable Diffusion 3 Now Available Experience this state of the art text-to-image model from our friends at stability.

We’re excited to announce a simpler way to make our AI tools work better for you at fal.ai. Our latest feature lets enterprise users fine-tune their models with user preferences collected directly through their apps. This new service starts today, making it easier to tailor your model to

We are thrilled to announce our official integration with Vercel! This partnership marks a significant step forward in our commitment to offering a seamless, efficient web development experience. At fal, we believe it’s important to provide developers with all the tools they need to enable generative AI in their

In this blog post we would like to showcase fal’s real-time Stable Diffusion APIs that are powered by Latent Consistency Models (LCMs). These models have been getting a lot of hype lately because they allow you to generate images very quickly around 150ms as opposed to 10 seconds with

Effortlessly serve your Python functions through a managed web server.

We demonstrate how to speed up hyperparameter tuning using fal-serverless, so you can quickly explore the search space and find the best model configuration.

We are launching fal-serverless, a cloud based Python runtime that simplifies infrastructure for teams who are building data pipelines, analytics, ML training and inference.