We’re thrilled to announce that MiniMax Hailuo 2.3 is now available on fal on day 0. This release delivers a major leap in video realism, camera control, and motion physics, making it MinMax's most capable generative video model to date. The model is available through Pro,

When using machine learning models in the real world, performance isn’t just about how fast your GPU can crunch numbers — it’s also about how quickly you can get your model there. Every second spent waiting on a checkpoint to load is a second your GPUs sit idle instead

We’re thrilled to announce that LTX 2.0 is now live on fal at day 0. LTX 2.0 brings next-level text-to-video and image-to-video generation, offering a blend of speed, fidelity, and flexibility for creators of all kinds. With Fast and Pro options supporting 1080p, 1440p, and 4K output,

Kling 2.5 Turbo Standard brings faster, more stable motion and tighter prompt adherence to image-to-video. It’s ideal for cinematic shots, product visuals, sports, and narrative scenes. The model builds on the 2.5 generation with upgrades in temporal consistency, camera control, and style stability, while reducing generation costs

We’re excited to introduce maestro, Beatoven.ai’s proprietary model for high-quality music and sound-effect generation - now available on fal.  Designed for creators, developers, and studios, maestro brings fast, high-fidelity audio generation directly to your workflow through two powerful APIs: Music and Sound Effects generation. Music Generation API

We are excited to announce the release of Reve now available from day 0 on fal. Reve is a state-of-the-art image generation model that brings visual intelligence, layout design, and editing into one seamless creative workflow. With text-to-image, image editing, and multi-reference generation, Reve gives creators precise control over composition,

We’re thrilled to introduce Meshy, now available on fal. Meshy is the newest addition to fal’s growing suite of generative media models. It's a powerful 3D generation model that turns words or images into high-quality 3D meshes ready for rendering, animation, and real-time applications. With text-to-3D,

We are pleased to announce the release of Veo 3.1, now available on fal from day 0. This latest evolution of Google DeepMind’s Veo model series brings a new level of cinematic control to generation, combining expressive visuals with native audio generation for synchronized, sound-integrated storytelling straight out

Moondream 3 Preview is now live on fal! The model is designed for real-world vision tasks from drones and robotics to medical imaging and retail. In this update, Moondream got a larger context window and has become much smarter. The model can now understand more sophisticated prompts and produce longer,

We’re excited to introduce Ovi, now available on fal on day 0. Built by Character AI, Ovi is the first open-source video model with native audio generation, delivering synchronized picture and sound from a single prompt with no post-production required. To help you get started, use coupon code Ovi

Develop and scale real-time generative image, video, audio, and vision apps faster with fal on Google Cloud Marketplace. Today, we’re excited to share that fal’s Generative Media Platform is now available on Google Cloud Marketplace. Teams can evaluate and purchase our production-ready model APIs directly through Google Cloud,

We’re excited to introduce Hunyuan Image 3, the next leap forward in open-source text-to-image generation. Built for creators with a vision, this model transforms words into visuals with unprecedented accuracy and artistry. Whether you’re aiming for photorealistic renders, experimental aesthetics, or characters captured mid-motion, Hunyuan Image 3 delivers

Image-to-video tools are everywhere right now. VEED's latest model, Fabric 1.0 allows you to generate faster and longer video outputs. It can animate any image, giving end-users the flexibility to go beyond preset avatars and create a wide variety of content. What is VEED Fabric 1.0?

We are excited to announce the release of Wan 2.5 now available from day 0 on fal. This latest model in the Wan family introduces new capabilities for both text-to-video and image-to-video generation. For the first time ever, Wan videos come alive with native audio generation, opening the door

We are pleased to announce the release of Kling 2.5 Turbo Pro, now available exclusively on fal. This latest model in the Kling family introduces enhanced capabilities for both text-to-video and image-to-video generation, expanding creative possibilities across a wide range of use cases. Kling 2.5 is designed for

While AI has transformed digital interactions, the physical world - with its dynamic environments and real-time demands - has remained out of reach. That’s why we’re excited to announce our partnership with Perceptron. Founded by the team behind Meta’s Chameleon multimodal models, Perceptron introduces breakthrough capabilities in

As image-editing models surge, teams keep asking for the same three things: speed, quality, and consistency. Seedream 4.0 delivers all three. It turns out 2K images in seconds and scales up to 4K when you need production headroom. From day 0 on FAL, these capabilities are in the hands

We’re excited to announce the release of Stable Audio 2.5, developed by Stability AI and now available through fal. the latest audio model from Stability and the first designed with enterprise-grade use cases in mind. Stable Audio 2.5 delivers a leap forward in both quality and creative

At fal, we live on the cutting edge of generative media models, but models are only one piece of a usable experience. Where and how AI is consumed and how users interact with it often gets too little attention. That’s why we’re thrilled to announce a partnership with

Today, we're excited to announce our partnership with Sonauto, bringing their latest v2.2 music generation model to the fal platform on day one. This integration delivers the highest quality vocals and more creative instrumentation with more depth than other music models—all accessible through fal's

For weeks now a secret image editing model has been making waves on LMArena. The consensus speculation has been Google was behind the so called "nano-banana" and today this speculation has been confirmed. nano-banana is Google's Gemini 2.5 Flash Image editing model and we are

Mirelo and fal are teaming up to bring complete experiences to AI video creation. With Mirelo SFX seamlessly integrated into fal’s platform, every video gains perfectly synced, production ready sound effects with no extra prompts or effort required. Together, we are making it effortless for creators and enterprises to

Recently Alibaba released Qwen Image a powerful and versatile image model. However this was just a preview of their ultimate plan: Qwen Image Edit, a SOTA open weights image editing model. Text Qwen Image Edit excels at text editing, beyond what we have seen from previous image editing models. For

In creative production, the difference between good and great often comes down to two things: having the right tool for the job, and getting it in place fast. That’s exactly what fal’s extensive model library delivers - instant access to hundreds of high-quality, ready-to-run AI models, from proven

We are proud to announce fal's inference and training endpoints Alibaba's Qwen Image model. It is has been an incredible month for generative media. We've been blessed not one, but two unbelievable high quality image models Wan 2.2 14b and Qwen Image. I