0:39 8 10 1 135 12.2K 128
fal
@fal
the generative media cloud. hiring https://t.co/JrbUk989MN. for support/discounts, e-mail us at support@fal.ai.
68.2KFollowers
5Following
2.9KPosts
1.2KMedia
2.5KLikes
0:39We're hosting AI Infra Day on Oct 20 with our friends at @a16z!
Join top engineering leaders from fal, @bfl_ai, @krea_ai, and @ElevenLabs as they share their experiences and lessons learned building and scaling AI infrastructure.
Come hang out: luma.com/fal-6m0z
Join top engineering leaders from fal, @bfl_ai, @krea_ai, and @ElevenLabs as they share their experiences and lessons learned building and scaling AI infrastructure.
Come hang out: luma.com/fal-6m0z
7 13 6 67 8K 14
Introducing H3 Max Relight, an easy way to change the lighting of any video.
Upload an existing video, then design your light in the built-in Lighting studio: pick colors, orbit each light around the subject, and dial in intensity and softness. H3 Max Relight relights every frame to match while preserving the original subjects, motion, camera movement, and audio. Go from flat daylight to golden hour, neon, or your brand palette, all without another shoot.
Powered by H3 Max, the #1 model for overall quality, prompt understanding, and aesthetics against leading video models.
Upload an existing video, then design your light in the built-in Lighting studio: pick colors, orbit each light around the subject, and dial in intensity and softness. H3 Max Relight relights every frame to match while preserving the original subjects, motion, camera movement, and audio. Go from flat daylight to golden hour, neon, or your brand palette, all without another shoot.
Powered by H3 Max, the #1 model for overall quality, prompt understanding, and aesthetics against leading video models.
0:24 11 26 9 296 22.9K 166
Vidu Q4 is now live on fal
- Image-to-video from a single first frame, with native audio
- Reference-to-video with up to 12 reference images and 3 voice clips for consistent characters and voices
- 3 to 16 second clips from 540p up to 4K
- Image-to-video from a single first frame, with native audio
- Reference-to-video with up to 12 reference images and 3 voice clips for consistent characters and voices
- 3 to 16 second clips from 540p up to 4K
0:15 7 10 4 76 9K 32
Nano Banana 2.1 is now on fal.
Google’s newest image model brings faster generation, better subject consistency, improved visual design, and mask-based editing.
Google’s newest image model brings faster generation, better subject consistency, improved visual design, and mask-based editing.
0:21 8 7 2 69 7.1K 20
Generate images and videos directly in Claude or ChatGPT Codex using the new fal Claude Connector and GPT plugin. No API Key required!
Watch the tutorial on YouTube: youtu.be/gSFCIxZSodQ?si…
Watch the tutorial on YouTube: youtu.be/gSFCIxZSodQ?si…
0:33 10 11 5 149 13.1K 103
fal is now available in ChatGPT and Codex.
Generate media with fal, then view and use it without leaving your chat.
- Browse generated images and videos directly in the conversation
- Access your fal Media Library from ChatGPT
- Pin your media library to the sidebar to quickly bring assets into any chat
Your creative assets, now where you work.
Generate media with fal, then view and use it without leaving your chat.
- Browse generated images and videos directly in the conversation
- Access your fal Media Library from ChatGPT
- Pin your media library to the sidebar to quickly bring assets into any chat
Your creative assets, now where you work.
0:30 20 23 8 234 33K 120
Nano Banana 2.1 is now available on fal
Google's newest image model, Gemini Nano Banana 2.1
Significantly faster generation than Nano Banana 2
Major gains in visual design, mask-based editing and subject consistency
Google's newest image model, Gemini Nano Banana 2.1
Significantly faster generation than Nano Banana 2
Major gains in visual design, mask-based editing and subject consistency
0:30 16 29 3 306 22.2K 90
Kandinsky 6.0 is now live on fal
- Pro for cinematic, high-fidelity generation
- Lite for fast, low-cost iteration
- Native synchronized audio
- Built-in upscaling, plus standalone VSR and VSR Lite for video super-resolution
- Pro for cinematic, high-fidelity generation
- Lite for fast, low-cost iteration
- Native synchronized audio
- Built-in upscaling, plus standalone VSR and VSR Lite for video super-resolution
0:18 7 17 5 197 15.2K 111
We teamed up with @bria_ai_ and @ltx_io for SF Tech Week, bringing together people from companies including Google, Adobe, Canva, ByteDance, Luma AI, and Hedra.
Thanks to everyone who joined!
Thanks to everyone who joined!
2 2 2 49 4.7K 1
Big launch from the Manus team.
Excited to see H3 Max, our post-trained video model, integrated into Manus 2.0.
Excited to see H3 Max, our post-trained video model, integrated into Manus 2.0.
Manus
8 12 1 196 19.5K 64
Last week, we brought the generative media community together in San Francisco for our GenMedia Conference 2026.
We revisited Pixar’s early days and how AI could lower filmmaking costs while keeping people in creative control.
Thanks to our speakers and everyone who came to San Francisco ready to share what they’re making and take part in this ever-evolving conversation.
We revisited Pixar’s early days and how AI could lower filmmaking costs while keeping people in creative control.
Thanks to our speakers and everyone who came to San Francisco ready to share what they’re making and take part in this ever-evolving conversation.
1:20 10 4 0 91 7.4K 14
H3 Max Reference-to-Video now supports first, middle, and last frame control.
Set your keyframes, choose when the middle frame appears, and add image or video references to guide the scene.
Shape how your shot starts, unfolds, and ends.
Set your keyframes, choose when the middle frame appears, and add image or video references to guide the scene.
Shape how your shot starts, unfolds, and ends.
0:21 27 14 8 275 22.2K 177
If you missed GenMedia Conference 2026, FOMO-not! Our official recap Vlog is live on YouTube!
youtu.be/vBjF5nkx4nI?si…
youtu.be/vBjF5nkx4nI?si…
1 3 2 40 8.3K 7
Grok Imagine Video 1.5 Lite is now available on fal
The lightweight model in the Grok Imagine video family
Text-to-video and image-to-video with native audio, 1 to 15 seconds
480p, 720p and 1080p output across 7 aspect ratios, from 16:9 to 9:16
The lightweight model in the Grok Imagine video family
Text-to-video and image-to-video with native audio, 1 to 15 seconds
480p, 720p and 1080p output across 7 aspect ratios, from 16:9 to 9:16
0:41 10 6 4 85 9K 19
Introducing fal Recast, an easy way to change any character in one click.
Upload an existing video + a reference photo of your new character. fal Recast changes who’s on screen while preserving the original motion, camera movements, cuts, and audio. Create character variations, adapt campaigns for different audiences, all without another shoot.
Powered by H3 Max, the #1 model for overall quality, prompt understanding, and aesthetics against leading video models.
Upload an existing video + a reference photo of your new character. fal Recast changes who’s on screen while preserving the original motion, camera movements, cuts, and audio. Create character variations, adapt campaigns for different audiences, all without another shoot.
Powered by H3 Max, the #1 model for overall quality, prompt understanding, and aesthetics against leading video models.
0:28 50 73 45 1.2K 156K 830
FLUX 3 Image from @bfl_ai is now live on fal.
Precise image editing that preserves what you don’t change.
- Generates images in native 2K and 4K
- Combines up to 10 reference images
- Makes multiple targeted edits in one pass
- Supports detailed control over layout and composition
Precise image editing that preserves what you don’t change.
- Generates images in native 2K and 4K
- Combines up to 10 reference images
- Makes multiple targeted edits in one pass
- Supports detailed control over layout and composition
0:28 6 21 4 255 16.3K 99
Passing the Turing test is no small feat. Congrats to the @tavus team on the launch!
Tavus@tavus · Oct 1Introducing Griffin, the first model to pass the video Turing test.
48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video.
It’s the first Human Interaction Model (HIM).
48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video.
It’s the first Human Interaction Model (HIM).
1:49 5 5 0 95 11.7K 17
Video generation and coding agents are defining a new class of AI workload. Individuals are productively consuming enormous amounts of compute as part of their everyday work.
fal CTO @gorkem on “token market fit,” in conversation with MTS at our GenMedia Conference last week.
fal CTO @gorkem on “token market fit,” in conversation with MTS at our GenMedia Conference last week.
MTS@MTSlive · Sep 30fal CTO @gorkem says generative media just hit "token market fit," with professionals now spending entire workdays generating video with AI:
"Since then, it really reached professional level, and we call it token market fit. Generative media has reached token market fit."
"Can a single person productively spend a lot of tokens doing their work? Only coding agents have this in the AI market. No other AI sub-industry can spend this many tokens as video generation or coding agents."
"People are now sitting in front of a computer at work and generating video all day long. They are willing to spend all these tokens doing their work, and this is the biggest change in generative media in the last year."
@fal
"Since then, it really reached professional level, and we call it token market fit. Generative media has reached token market fit."
"Can a single person productively spend a lot of tokens doing their work? Only coding agents have this in the AI market. No other AI sub-industry can spend this many tokens as video generation or coding agents."
"People are now sitting in front of a computer at work and generating video all day long. They are willing to spend all these tokens doing their work, and this is the biggest change in generative media in the last year."
@fal
1:15 4 1 0 48 7.8K 10
Congrats to @HoloworldAI on the launch!
tong@tong0x · Sep 30RIP prompting. 2023–2026.
Introducing Ava Studio: your AI content team. Drop in your website, and it researches, scripts, and produces on-brand videos you can edit or ship.
RT + comment your website. We’ll build your first video campaign for free.
Introducing Ava Studio: your AI content team. Drop in your website, and it researches, scripts, and produces on-brand videos you can edit or ship.
RT + comment your website. We’ll build your first video campaign for free.
0:49 3 10 0 159 23.9K 168