Christos

Super fulfilled and energized hosting this 7-hour video hackathon with our friends at @fal @MuxHQ @zakariaornot at Overshoot. We’ve seen cool demos ranging from real-time moderation, to virtual tryon, to live podcasting to AI monitoring the situation. It’s a good remember how powerful video is as a computing interface and the most versatile medium. Thank you our judges @joshalphonse @Christos_antono @zakariaornot. And congrats to all the prize winners! 👏

I love using fal to make developing fal easier. Using GPT Image 2 + Seedance 2 and review and prompt instruction is done by Opus 4.7 with Claude Managed Agents

Announcing World Model Accelerator, fal's new product: fal.ai/wma We've spent years building the inference layer for generative media. In 2023, we shipped 30 FPS, low-latency, action-controlled diffusion APIs, years before anyone else. Fast forward to today and we've been powering foundational model companies across image, video, real-time speech-to-speech and action-controlled world models. Now we're opening it up. World Model Accelerator is the system behind it all. Our in-house inference engine hits SOTA performance on Hopper and Blackwell for Diffusion Transformer workloads, both causal and bi-directional. Built on fal Serverless, it scales seamlessly from 1 GPU to 1,000+. This is the same platform that's been running real workloads, at scale, for years. A new WebRTC gateway optimizes latency between users and GPUs (routing requests to the closest region), built on the same infra that powers our real-time speech workloads. And direct access to the fal Marketplace puts your model in front of enterprises spending hundreds of millions on generative media, with a real co-selling motion behind it. This is the infrastructure layer for world models.

Fal Redesign is here !! a claude code skill that redesigns any page you vibe-coded. uses gpt-image-2, flux-2, and claude opus 4.7 under the hood, all via fal. fully working, just super early. want to see how people use it. install directly in claude code: curl -fsSL raw.githubusercontent.com/fal-ai-communi… | bash launch in claude code: > redesign index.html all our skills can be found here as well github.com/fal-ai-communi…

@pozynta @fal Apologies for the inconvenience you can use this link fal.ai/models/openai/…

@fal why do you need to do early access??, this was only necessary for seedance 2

🚨 GPT Image 2 is live on fal, day 0! 🔤 Strong text rendering 🧭 Better layout + UI adherence 🛠️ Cleaner preserve-and-change edits 📷 Strong everyday photoreal output

@SwelmChannel @fal Apologies for the inconvenience you can use this link fal.ai/models/openai/…

@fal 404 Page not found!

@ssoydan_solo @fal Apologies for the inconvenience you can use this link fal.ai/models/openai/…

@fal Check the links please, they are unreachable.

Image to world + image to playable character to explore it! 🍻 Made this app using image-to-world through @theworldlabs, image-to-3D + auto-rigging through @MeshyAI on @fal, rendered with Spark.js + three.js

fal has been recognized on the #ForbesAI50 list! Grateful to be included alongside some of the most ambitious teams pushing the space forward. Thanks to our partners and customers for building with us 🚀 Full list: forbes.com/lists/ai50/

@PhilipJohnston @Starcloud_ @nvidia Epic work! Congrats @PhilipJohnston !

I am super excited to share that @Starcloud_ has raised a $170M Series A at a $1.1bn valuation to fuel our development of data centers in space 🚀 The round comes after the successful deployment of our first satellite, Starcould-1, a few months ago, which had the first @NVIDIA H100 on board and was the first to train an LLM in space. The funds will be used to develop our third satellite, which aims to be cost-competitive with Earth-based data centers in terms of AI inference cost. The round was led by @Benchmark and @EQT Ventures, and we are excited to welcome Benchmark GP, @Chetanp Puttagunta, to our board. We are also excited to welcome other new investors, including the world's largest infrastructure fund, @Macquarie Capital, @SevenSevenSix 7️⃣7️⃣6️⃣, Manhattan West, Adjacent, Carya, GSBackers, and Harpoon. We are very grateful for the continued support of existing investors, including @NFX, @NebularVC, @YCombinator, @FUSE_VC, @Soma_Capital, 3Capital Partners, Wyld VC, Tiny VC, and Taurus Ventures. Onwards!

Now, generate ANY playable character from an image, all in Unreal Engine 5, powered by @fal and featuring @jfischoff 🎮

Never lost in home court

@elonmusk Buy Revolut, it's the best consumer fintech product ever made

𝕏 Money early public access will launch next month

We are now live on @fal → Video Agent → Video Translation → Digital Twin → Avatar IV Go add it to your workflow today!

To celebrate nano-banana-2 launching on @fal , I built FalSprite, sprite sheet generator that turns a text prompt into game-ready animations. One fal.ai key powers the whole pipeline: → nano-banana-2 for image generation → BRIA for background removal → OpenRouter LLM for prompt rewriting ~$0.20 per generation. Try it live or fork it: 🔗 falsprite.vercel.app 🔗 github.com/lovisdotio/fal… Thanks @BlendiByl for the help on this 🙏

Fourth drop on @fal performance blog. Our resident GPU communications expert Ismayil is revealing one of the many interesting things we do on comms-computation overlap in our inference engine. Async Ulysses. blog.fal.ai/ulysses-unboun…

Watching a castle emerge from noise in Minecraft is pretty damn cool 🏰

Hyper-Precise Virtual Try-On LoRA for FLUX.2 [klein] 9B Edit Hosted on fal and Open source Upload 1 person photo + 2 clothing references → realistic try-on result 3 images in → 1 styled output Open weights on HuggingFace

Generate ANY sprite sheet + 2D side-scroller map, feat Luffy 🍖

Osimhen's journey is one of the most powerful stories I've ever come across. That's why I made this video for @victorosimhen9