@fal
Account based inUnited States
About this account
- Account based in
- United States
- Connected via
- Web
Account-level information from X, not a live location or the device used for a specific post.
the generative media cloud. hiring https://nitter.cf/t.co/JrbUk97BXf. for support/discounts, e-mail us at [email protected].
San Francisco
Joined May 2009
- Tweets2.8K
- Following5
- Followers67.4K
- Likes2.5K
Introducing H3 Max, new post-trained video model by fal Research.
H3 Max ranks #1 for overall quality, prompt understanding, and aesthetics against leading video models, on both first-party and third-party independent evaluations while generating a 5-second 720p video under 3 seconds.
H3 Max is 50% off for the next week, making it the highest quality, fastest and cheapest model for overall video generation tasks.
Playable ads are such a creative use case for generative media. Congrats to the @layer_ai team on the launch!
“Anyone not using Layer is 2.5 steps behind."
@matejlancaric, after surveying 115 UA studios for his Q1 2026 report
Here's what he's talking about:
bit.ly/4AEVufT
Video Insert is now live on H3 Max, the fastest video model on the market and ranked #1 for video editing.
With this new endpoint you can now generate and then insert a new scene into an existing video with H3 Max. Guide the scene with a prompt, reference images, or reference videos, then return to the original footage.
Take your original videos and then add a seamless new scene within it.
Join fal, @bria_ai_ and @ltx_io for a builders’ breakfast during SF Tech Week, where we’ll dig into how to build generative media pipelines with open-weight models.
Lightning talks, panel + Q&A, and espresso.
partiful.com/e/9OQfXbXauvFiB…
Eleven v4 and Eleven v4 Turbo are now available on fal.
ElevenLabs' most expressive text-to-speech, directed with inline audio tags like [whispers] and [laughs]. Emotion shifts mid-sentence, character voices and speech in 100 languages.
Eleven v4 Turbo brings the same voices at low latency for real-time agents.
Try it here today!
Eleven v4
fal.ai/models/elevenlabs/tts…
Eleven v4 Turbo
fal.ai/models/elevenlabs/tts…
Kling 4.0 is coming soon to fal.
The next generation brings major upgrades in visual realism, creative control, narrative coherence, audiovisual quality, multi-keyframes, lip sync and more.
Kling 4.0 Flash is now available in early access to a limited group of users. Stay tuned.
The tote bags at our conference received so much love! We worked so hard on this mini-capsule for GenMedia Conference so thank you all for the kind words. 😵😭
Nearly every element was made and produced from scratch.
- shell fabric: custom dyed nylon fabric in light sage
- cord: custom developed cord 8mm cord
- inside snap
- metal d rings
- fal logo silver carabiners
- heat transfer logo
- double patch pockets
- care labels
Some say they can be turned inside out.
Made at fal design lab / @HyunjungLee_ with so much attention to detail down to the care label designs / thank you to our production partners!
We’re excited to share that US-hosted Seedance 2.0 now supports 1080p and 4K video generation on fal.
This follows the 1080p rollout for US-hosted Seedance 2.5 last week, bringing higher-resolution generation to fal customers on US-hosted infrastructure.
For customers who need face restrictions lifted, get in touch and our team can guide you through the process.
Try it here today.
Text-to-Video: fal.ai/models/bytedance/seed…
Image-to-Video: fal.ai/models/bytedance/seed…
Reference-to-Video: fal.ai/models/bytedance/seed…
fal retweeted
We're bringing online 1 GW of net new compute in the next 24 months, and I'm hiring for Tactical Compute Ops in SF to help make it happen.
You'll work directly with me and @nina_gerov, one of the best ops leaders I know.
Finance/IB, Legal, and other backgrounds are more than welcome.
DM me with a few lines on yourself and why you'd want to join.
Available across all Seedance US 2.5 endpoints:
• Text to Video
fal.ai/models/bytedance/seed…
• Image to Video
fal.ai/models/bytedance/seed…
• Reference to Video
fal.ai/models/bytedance/seed…
1080p is live now on all three.
Gemini 3.8 Flash TTS and Gemini 3.8 Flash Lite TTS are now live on fal!
- Design custom voices from natural language, from character and accent to tone and delivery
- Direct performances line by line with precise control over pacing, emotion, dialect, and conversational cues
- Generate consistent long-form speech and natural multi-speaker dialogue across 100+ languages and dialects
Try it here today!
Gemini 3.8 Flash TTS
fal.ai/models/google/gemini-…
Gemini 3.8 Flash Lite TTS
fal.ai/models/google/gemini-…
One of the founders of Figma Weave, @Ygurzeev joins fal’s Head of Operations @nina_gerov on our stage to discuss how teams can build on each generation instead of starting over.
Unlike a prompt box, Weave turns every generation and edit into a node teams can branch from, remix, or redo, creating a repeatable system that’s harder to copy than the models themselves.
Here's @jcjohnss of World Labs joining @venturetwins of a16z on our stage to explain the work he co-leads: building generated worlds from space and geometry so they stay consistent as the camera moves.
When the room and everything in it stay put, people can build a game level, return to a scene for more shots, or train a robot in the same environment instead of simply watching a generated world.
Welcoming @caroingeborn of Luma, Daniel Berkovitz of LTX, and Marwan Genena of Ideogram to join us on stage to discuss how model labs compete in a relay race: each breakthrough becomes the next lab’s starting point, so no lead lasts long.
Can excellence in one lane still create a moat, and what do open weights unlock beyond transparency?
Jeffrey Kember of NVIDIA and @stephanbugaj of JioStar were both at Pixar when many in the industry still resisted CGI, and they join us on stage to explain how teams found practical uses for it before everyone came around.
For Stephan, vision and philosophy set the direction, but a rational process brings a new tool into everyday use; at Pixar, that combination helped make CGI a standard part of filmmaking.
Albert Cheng of Amazon MGM Studios joins investor @stevejang on our stage to discuss who gets to tell stories when production costs no longer stand in the way.
Pixar was once an outsider that changed filmmaking by bringing animators and technologists together; generative media can now help more creators make ambitious, high-quality stories that were once too expensive to attempt.
