fal.ai Blog | Generative AI Model Releases & Tutorials

Ulysses Unbound: Experiments in Communication–Computation Overlap

Ulysses Unbound: Experiments in Communication–Computation Overlap

As video diffusion models scale, sequence lengths get uncomfortably large. A practical answer is context parallelism, and within that family, Ulysses is the canonical approach. The core idea is simple: full sequence, sharded heads. It maps well to modern GPU clusters built for high-throughput all-to-all communication, while still letting you

Instruction-level control with Inline Elementwise ASM in Triton

Instruction-level control with Inline Elementwise ASM in Triton

Triton is a DSL (Domain-Specific Language) which makes it deceptively easy to write fast GPU kernels in Python since it abstracts all the nuances of writing a pure GPU kernel from scratch, such as manual memory hierarchy handling, synchronization, and low-level launch configuration while still producing highly optimized GPU code.

Kling 3.0 Prompting Guide

Kling 3.0 Prompting Guide

Kling 3.0 is designed to understand cinematic intent, not just visual descriptions. The model performs best when prompts are written like directions to a scene rather than a list of objects. Clear structure, explicit motion, and intentional shot language all lead to noticeably better results. For developers building with

Kling 3.0 is Now Available on fal

Kling 3.0 is Now Available on fal

We're pleased to announce the release of Kling 3.0, now available on fal from day zero. Kling 3.0 represents a new state-of-the-art generation stack for video and image creation, built for structured storytelling rather than isolated clips.

Crafting Efficient Kernels with Epilogue Fusion

Crafting Efficient Kernels with Epilogue Fusion

In many ML workloads, a GEMM is followed by small operations like bias, activation, scaling, or type conversion. These ops are cheap in math, but they often cost extra global memory traffic (store GEMM result, read it back, write again). Epilogue fusion is a way to avoid this, we can

Grok Imagine is Now Available on fal

Grok Imagine is Now Available on fal

We’re excited to introduce Grok Imagine, a new multimodal release that brings five new model endpoints to a single creative stack, covering both generation and editing across image and video workflows. With these additions, teams can move faster from idea to polished output, whether they’re generating assets from

Chasing 6+ TB/s: an MXFP8 quantizer on Blackwell

Chasing 6+ TB/s: an MXFP8 quantizer on Blackwell

We built an MXFP8 quantizer in CuTeDSL that hits 6+ TB/s on B200. The kernel writes scale factors directly into the packed layout that Blackwell's block-scaled Tensor Cores expect, so downstream GEMMs can consume them without an additional pack step. MXFP8 is a microscaling format (from the

LTX 2.0 is Now Available on fal

LTX 2.0 is Now Available on fal

We’re thrilled to announce that LTX 2.0 is now live on fal on day 0. LTX 2.0 brings next-level text-to-video and image-to-video generation, offering a blend of speed, fidelity, and cinematic control for AI creators. LTX 2.0 is a state-of-the-art open-source model, giving developers full freedom

Chatterbox Turbo is now available on fal

Chatterbox Turbo is now available on fal

Chatterbox Turbo is an open-source, ultra-fast text-to-speech model built for real-time voice AI. It combines sub‑150 ms time to first sound with expressive paralinguistic prompting and instant voice cloning, so agents can speak naturally in the voices your users expect. Available day 0 on fal, so you can try

Our Series D: Scaling fal

Generative Media is growing faster than imagined. New use cases, from design to the future of commerce, are emerging every day. To meet this accelerating demand, fal is continuing to scale. Today, we're excited to share that fal has raised a $140M Series D, welcoming new investors Sequoia,

Pika API is now powered by fal

Pika API is now powered by fal

We’re excited to share that Pika, the leading AI-powered video platform, has partnered with fal to bring its powerful Model 2.2 to our high-performance inference infrastructure including the model’s signature features Pikaframes (multi-key frame interpolation) and Pikascenes (build a scene from exact character, object, wardrobe and setting

Kling 2.6 is Now Available on fal

Kling 2.6 is Now Available on fal

We are pleased to announce the release of Kling 2.6, now available exclusively on fal on day 0. This latest model in the Kling family introduces native audio generation for both text-to-video and image-to-video generation, expanding creative possibilities across a wide range of use cases. Kling 2.6'

Seedream 4.5 is Now Available on fal

Seedream 4.5 is Now Available on fal

Seedream 4.5 is Now Available on fal. We're excited to bring Seedream 4.5 to fal at day 0. Latest update doesn't chase flashy new capabilities—it doubles down on execution quality where production workflows actually break down.

Introducing Kling O1 Video Available Exclusively as an API on fal

Introducing Kling O1 Video Available Exclusively as an API on fal

We’re pleased to announce the release of Kling O1 , the newest state-of-the-art video editing model, now available exclusively on fal on day 0.

Training FLUX.2 LoRAs

Training FLUX.2 LoRAs

FLUX.2 on fal offers two powerful pathways for model customization: Text-to-Image LoRA training, which teaches the model a new style, character, product, or aesthetic; and (Multi) Image-to-Image LoRA training, which teaches the model how to transform one image into another. Both trainers are easy to use and designed to

FLUX.2 Is Now Available on fal

FLUX.2 Is Now Available on fal

We’re pleased to announce the release of FLUX.2 , the newest state-of-the-art image generation and editing model, now available on fal on day 0. FLUX.2 pushes visual quality, realism, and controllability forward in a major way. FLUX.2 Pro comes in two powerful models: * Text-to-Image: https://fal.ai/

ImagineArt 1.5 Is Now Live on fal

ImagineArt 1.5 Is Now Live on fal

We’re excited to launch ImagineArt 1.5 on fal. ImagineArt 1.5 delivers lifelike realism, sharp text rendering, and professional aesthetics, making it ideal for creators, designers, and teams who need polished visuals on demand. What’s new in ImagineArt 1.5 Ultra-realism Surfaces, lighting, skin, and textures render

NanoBanana Pro Is Now available on fal

NanoBanana Pro Is Now available on fal

We’re excited to introduce NanoBanana 2, the state-of-the-art image generation model now available on fal at day 0. With two powerful endpoints for text-to-image and image-to-image, NanoBanana 2 gives creators unparalleled control over visual output.

Comparing the Best AI Upscalers for Video and Images

Comparing the Best AI Upscalers for Video and Images

In any modern AI creative workflow, upscalers play a critical post-processing role. They take the raw generations from diffusion or generative video models (often limited to 720p resolution) and convert them into production-ready assets suitable for film, design, or print.

Key Takeaways from the First Generative Media Conference

Key Takeaways from the First Generative Media Conference

There have been a lot of AI conferences, but none focused on generative media. Until now. On October 24, 2025, inside the Ferry Building overlooking the San Francisco bay, we hosted the inaugural Generative Media Conference. 300 of the leading founders, researchers, studio heads, architects, advertisers, and investors in the

Welcoming the Remade Team to fal

Welcoming the Remade Team to fal

Today, we’re excited to announce that fal has acquired Remade, a YC-backed startup building powerful tools for generative media creation. Remade has spent the last two years pushing the boundaries of what’s possible with generative media, training custom models, building unique product experiences and contributing to the open-source

Sora 2 & GPT Image 1 are now available on fal

Sora 2 & GPT Image 1 are now available on fal

We’re thrilled to announce that Sora 2 and GPT Image 1 are now available on fal.ai. These groundbreaking generative AI models push the boundaries of what’s possible in video and image creation. Whether you’re building creative tools, social media content, or interactive experiences, these new releases

Google Veo 3.1 vs 3.0: Worth the Upgrade?

Google Veo 3.1 vs 3.0: Worth the Upgrade?

What Changed Google released Veo 3.1 in mid-October 2025. Both versions run on identical veo-3.0-generate-001 architecture. This is refinement, not reinvention. Improvements come from better training data and enhanced post-processing, which shapes everything about the upgrade decision. Three material improvements define this release: Synchronized audio generation directly from

Sima Upscaler Is Live on fal!

Sima Upscaler Is Live on fal!

We’re excited to introduce the Sima Labs image and video upscaler, now available on fal. This new upscaling suite brings crystal-clear enhancement to both images and video, powered by advanced AI models that preserve fidelity, colour, and detail at every level.

Hunyuan Image 3.0 vs 2.0: Upgrading Your GenAI Image Generator

Hunyuan Image 3.0 vs 2.0: Upgrading Your GenAI Image Generator

Strategic Leap Forward Tencent's Hunyuan Image 3.0 represents a significant advancement in open-source text-to-image generation. With 80 billion parameters (13 billion active through MoE architecture), it's now the largest available open-source model in this space. But size alone isn't the story. The core