Really happy to share this new version of wan animate that will be faster and better looking ;) on @fal , I work hard on it the last few days. Hope you will like it ! It can be long if you process long video, so test with short one first ! fal.ai/models/fal-ai/wan/v2.… fal.ai/models/fal-ai/wan/v2.… Little tips for devs, activate “use_turbo” in api, for normal user you can just use it on the playground and keeping original parameter for best result ( you can change to 720p for quality ) Other tips, test first with short video before to process long video as it can be long to render. and don’t process more than 20 s, its better !

We’re thrilled to announce that fal has acquired @Remade_AI, a YC-backed startup building advanced tools for generative media creation. The Remade team has pushed the boundaries of AI creativity, from building an intelligent canvas for marketing teams, to open-souring video LoRAs used by thousands of creators and developers. They are joining fal to help accelerate the next generation of creative infrastructure for developers around the world. Welcome to the team @BlendiByl, @Christos_antono, @rehan_shei and @alexgmatt. It’s amazing to have you on board!

Finally starting to see generative media in the wild. Looks like we're graduating from prototypes and early adopters to mass adoption.

This team. @fal

Reaching the scale to host your own conference is a massive milestone for a company. Since @fal’s inaugural Generative Media Conference is this Friday, I sat down with @gorkemyurt to dig into the last 3 years of their journey. Their 10/24 conference has an insane speaker lineup with lots of real-world use cases of generative media in action. The preview video below is just one example (we used fal’s platform to create all the visuals). Aside from the fun we had turning me into George Clooney and making a giant 3-ton Roomba cat destroy our podcast studio, what stood out was how far all of these models have come in the last few years -- and how easy it is to get started with fal and play around so many different options. There’s a ton of interesting technical optimizations and developer-focused decisions that made that experience possible, so it was great to hear Gorkem unpack all of their unique company and product building choices. One of the more interesting ones that they hardly ever talk about is their pivot (when I invested back in 2022, it was a completely different product for data teams), so it was fun to get into that story as well. Full conversation below, hope you enjoy it!

Super happy to collaborate with the @digitalocean team to bring easy access to generative media to even more customers!

🎨 Introducing fal Sandbox. You can now instantly run the same input across multiple models. Compare hundreds of models from fal’s platform side-by-side for speed, quality, and cost.

Fun times in SF this October!

VEED Fabric 1.0 💥 The world’s first-ever AI talking video model. Now, available on API on @fal. – 60x cheaper – 7x faster 🚨 Giving away up to $2000 in credits to 5 lucky users. Want access? • Retweet • Leave a comment Winners announced via DMs.

Here is a video about our recent release: Kling 2.5 Turbo piped.video/watch?v=Jc_Hm4BH…

@fal we needed a way to ensure fast request processing, so we built an internal scheduler and we just added rolling deployments. The deployment automatically manages traffic spikes by considering current load and autoscaling. Want to help us power the generative media revolution? Check out at fal.ai/careers

Congrats to team @PhotaLabs 👏

🚨 Seedream 4.0 is launching on fal day 0, #1 model for multimodal image generation and editing. With exclusive discounts. 🎨 Text-to-image and image editing in one powerful model 📸 Natural language control with pixel-perfect precision 💰 Just $0.03 per generation! Volume discounts are available, reach out.

Nanotech these days 🤯

🚀 Day 0 access alert! We're keeping our promise to deliver the latest models instantly. Grab your $10 coupon (first 1000 users only!) to test drive our brand new model on the platform: fal.ai/coupon-claim/NANO-BAN… ❤️ Like & RT for more coupon drops coming soon!

Late august evenings are the best

Did you try @TencentHunyuan World model on @fal?

GPT-5's smaller leap from GPT-4 shows we're topping the LLM scaling curve. It's time for SLM-driven agents, hybrid systems, vertical integrations.

Traditional LLM scaling is hitting the top of the sigmoid curve. What's next?

Ok, now I want an image-to-world model and then eventually also a video-to-world model.