MiniMax Text-to-Speech Models now available on fal fal is thrilled to announce our partnership with MiniMax, a multimodal innovator known for its advanced video, image and audio models. To experience the cutting-edge MiniMax Text-to-Speech (TTS) Models firsthand, visit the model gallery on fal today. Introducing MiniMax Text-to-Speech Models The MiniMax TTS API
CassetteAI Music Generator Model now available on fal We're thrilled to announce that CassetteAI's Music Generator and Sound Effects Generator models are now available on fal's powerful generative AI platform. This integration allows you to generate high-quality tracks in record time and create stunningly realistic sound effects in seconds. Unprecedented Speed
Announcing fal Models Availability in Adobe’s Ecosystem At fal, we’re on a mission to build the fastest inference platform for generative media—helping creators bring their ideas to life with speed, flexibility, and control. That’s why we’re excited to partner with Adobe as they expand choice for creators by integrating additional generative AI models
Launch of fal AI integration on Vercel We are excited to announce the release of our latest AI native integration on Vercel, designed to simplify access to GenAI models on fal for Vercel users. Unlock New Possibilities with Our Integration * Access to latest video models: Transform static images into dynamic video content with our state-of-the-
Pika Models Now Available on fal We’re excited to unveil Pikaffects, Pikascenes, the Pika family of models, now available on fal. Through our partnership, these cutting-edge tools are ready to transform your creative projects with stunning visuals and seamless performance. Curious to see them in action? Check out the model gallery on fal. Pika
Topaz Video AI Upscaler now live on fal fal is partnering with Topaz Labs to offer their groundbreaking Video AI Upscaler, now available on the fal model gallery. The video upscaler transforms low-resolution and degraded video into high-definition quality. Video Upscaler by Topaz Video AI This new video upscaler by Topaz Labs is a powerful video
Vidu 2.0 Models Live on fal fal is partnering with Vidu, a cutting-edge video generation platform designed to help enterprises and developers seamlessly create and scale video production. With advanced multimodal capabilities – such as start-end frames and reference images – and robust performance, Vidu makes it easy to generate high-quality, visually stunning videos tailored
Veo2 Image-to-Video now available on fal After the tremendous success of Google's Veo 2 text-to-video model, we're thrilled to announce our newest partnership with Google to bring you Veo2 Image-to-Video capabilities first in the market. 0:00 /0:08 1× Just weeks after the initial release, this expansion
New Image Editing Model from Easel AI Now Available on fal fal is thrilled to announce the latest advancements from Easel AI, bringing cutting-edge face and body swap technology to our platform. With enhanced single-player and multiplayer capabilities, Easel AI delivers stunningly realistic results while preserving users’ likeness and maintaining the aesthetic integrity of every image. Whether you’re
New LTX Video Model Live on fal fal is excited to announce a new version of LTX Video by Lightricks. Key updates include improved quality, longer video generations, and more control using new conditioning and key frames. The update also supports commercial licensing. To try out the LTX Video models, visit the model gallery on fal. Updates
Juggernaut FLUX Series: Redefining Photorealism At fal, we’re committed to pushing the boundaries of AI-powered creativity. Today, we’re excited to announce our partnership with RunDiffusion, to take photorealism to unprecedented heights. With the introduction of the Juggernaut FLUX series, RunDiffusion has set a new standard in AI image generation—and together, we’
ElevenLabs Audio Suite: Next-Generation Voice and Audio AI Now on fal Today, we're excited to announce our partnership with ElevenLabs to bring their complete suite of state-of-the-art audio AI models to the fal platform. This integration delivers unprecedented voice quality, audio processing capabilities, and multilingual support—all accessible through simple, developer-friendly APIs. Comprehensive Audio AI
New BRIA AI Image and Editing Models Live on fal fal is partnering with BRIA AI, a pioneering Generative AI platform that transforms how businesses create and modify commercial-first rich visual media while eliminating copyright and privacy infringement risks. To try out BRIA AI’s models, visit the model gallery on fal. Introducing BRIA AI BRIA AI delivers commercial-
Mastering Video Generation with Veo 2: A Comprehensive Guide 🆕We just lowered the price of Veo 2 on fal.ai by 50% to make the new generation of video models accessible to anyone. Veo 2 (Google's latest text-to-video generation model, that is available directly through fal) is pushing the boundaries of what's possible
Veo2: State-of-the-Art Video Generation Now on fal P.S: Follow our X account for coupons to use Veo2 for free: https://x.com/FAL/status/1893014729393594837 We're thrilled to announce that Veo2, Google's cutting-edge video generation model, is now launching via API on fal. Click here to play with it. This integration
fal Raises $49M Series B to Power the Future of AI Video Generative media is expanding faster than we ever imagined, and video is its next frontier. fal has raised a $49M Series B to fuel our mission: building the core infrastructure for AI-driven media creation. We’re thrilled to share we raised $49M in Series B funding from Notable Capital
Introducing the AI Video Developer Starter Kit Today, we are thrilled to announce the release of the AI Video Starter Kit by fal. As AI video technology experiences unprecedented growth, fal is at the forefront of this revolution as the leading developer platform for generative video. The AI Video Revolution The landscape of AI-generated video is
Introducing PlayDialog: The Next Evolution in Conversational AI Today we're announcing our partnership with PlayAI and launching their PlayDialog model on the fal platform. PlayDialog is the world's first emotive, contextual AI voice model for conversations. With industry-leading latency of just 350ms, PlayDialog delivers the most natural-feeling synthetic speech experience available today.
Introducing MiniMax (Hailuo) video-01-Live: Transform Static Art into Dynamic Materpieces We are thrilled to announce our partnership with MiniMax to bring you the revolutionary Hailuo video-01-Live model (“Live”), now available on our platform. Designed to preserve intricate artistic details while delivering ultra-smooth animation, Hailuo Live pushes the boundaries of what’s possible in image-to-video (I2V)
New SOTA Virtual Try-On Model by FASHN live on fal fal is partnering with fashn.ai to offer the first commercially available virtual try-on model. To play around with the new model now, check out the playground page here on fal. Introducing FASHN’s Virtual Try-On Solution FASHN’s virtual try-on solution is a pipeline composed of
Introducing the FLUX Portrait Trainer 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
Announcing red_panda by Recraft 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"
Announcing Stable Diffusion 3.5 Large & Turbo by stability.ai 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
Training FLUX Style LoRA on fal 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
Announcing FLUX1.1 [pro] by BFL and FLUX [dev] speed improvements 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 🫐"
![Announcing FLUX1.1 [pro] by BFL and FLUX [dev] speed improvements](https://storage.ghost.io/c/0e/15/0e15ee8a-bd95-4b71-9258-950f77f4d196/content/images/size/w600/2024/10/unnamed.png)
