Volkan Aydıngül (@vaydingul) profile picture

ai @fal

Joined December 2019
Photo by Volkan Aydıngül (@vaydingul)Photo by Volkan Aydıngül (@vaydingul)Photo by Volkan Aydıngül (@vaydingul)Photo by Volkan Aydıngül (@vaydingul)Photo by Volkan Aydıngül (@vaydingul)Photo by Volkan Aydıngül (@vaydingul)Photo by Volkan Aydıngül (@vaydingul)Photo by Volkan Aydıngül (@vaydingul)Photo by Volkan Aydıngül (@vaydingul)Photo by Volkan Aydıngül (@vaydingul)
Volkan Aydıngül retweeted
7
900
25
6,080
60,380
Volkan Aydıngül retweeted
The Dolby poster for ‘DUNE: PART THREE’ has been released. In theatres December 18.
11
217
16
2,652
53,530
Volkan Aydıngül retweeted
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai. FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds. For the next three weeks, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
147
180
212
1,489
562,517
This is so cool! Everyone should try relight on @fal
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.
1
1
7
688
Volkan Aydıngül retweeted
Rabbim kimseyi tokensız bırakmasın ne zor olduğunu yaşamıyan bilemez 🤲 3-5 token için eli ayağı titreyerek reset bekleyen binlerce insan mahvolmuş durumda
27
15
4
351
20,332
Volkan Aydıngül retweeted
Its over. From now on everything will be invented by Sakana AI.
Sakana AI welcomes Jürgen Schmidhuber as Chief Scientific Advisor. sakana.ai/schmidhuber/ Sakana AI is incredibly proud to announce that Jürgen Schmidhuber, universally recognized as the father of modern AI, is officially joining Sakana AI as Chief Scientific Advisor. For nearly four decades, Jürgen has explored how machines can learn to learn. His foundational work in the 1990s drove core advancements in deep learning and established early frameworks for world models. Crucially, his pioneering innovations in meta-learning opened the very path toward recursive self-improvement. These ideas have already shaped our own research, from the Darwin Gödel Machine to The AI Scientist. Now Jürgen will help guide our newly formed RSI Lab, whose objective is to trigger a compounding cycle of scientific discovery aimed at improving machine intelligence. We are assembling a critical mass of world-class experts in Tokyo to make this a reality. Welcome, @SchmidhuberAI !
26
65
4
1,580
112,944
Volkan Aydıngül retweeted
claude’dan sonra iki haftadir codex kullaniyorum codex pismanliktir
36
2
2
269
64,022
Volkan Aydıngül retweeted
jev aklı bunu da dusundu
jev is INSANE. in 40 seconds it broke down 724 live ads from 37 brands. every hook. every format. offer. cta. awareness stage. landing page mismatch. used 9 cents of tokens. (will be avail in @stealads + mcp)
9
8
399
61,466
Super cool launch of lip syncing capabilities
H3 Max Lip Sync is now live on fal. Upload one photo and one audio clip and get back a lip-synced video in seconds, with natural expression and movement, in any language. In our evals, H3 Max Lip Sync ranks #1 for both quality and speed, with a median generation time of just 11 seconds. Try it now on fal.
4
29
2,067
Volkan Aydıngül retweeted
i built a first-person horror game you wake up in a hospital, explore the rooms, and make choices to find your way out. powered by H3 Max Turbo from @fal give it a try: hospital.vamonke.com
40
13
6
172
16,525
Volkan Aydıngül retweeted
kids these days will never know the feeling of making matplotlib charts by hand
69
209
43
3,010
198,418
Volkan Aydıngül retweeted
One image. Every angle. Rendered under 3 seconds. Multi-angle is now live for H3 Max on fal Set the horizontal and vertical camera angle in degrees and H3 Max moves through the scene from a single viewpoint. Shape, position, and materials stay put as the perspective changes, so the angles read as the same moment rather than separate generations.
30
68
37
521
97,969
Volkan Aydıngül retweeted
pov: me explaining how @fal will create a h3 max turbo ultra that will inference in negative time
7
5
1
59
3,960
Volkan Aydıngül retweeted
fal research strikes again! #1 video model in the world, verified by @DesignArena not only the best quality, but the fastest as well
BREAKING: MiniMax H3 Max sets the new Pareto Frontier for video generation, nearly 50x faster than the base model. This model is post-trained by @fal on @MiniMax_AI H3, and it's in a league of its own: no other Image to Video model on the arena delivers higher preference at a lower generation time. Its Image-to-Video generation time is just 6.4 seconds, 18x faster than average, and its Text-to-Video generation time is just 4.7 seconds, 24x faster than the average. Huge congratulations to the @fal team on this release!
6
1
57
2,023
Volkan Aydıngül retweeted
Introducing fal Research The post-training arm of fal, building frontier RL infrastructure for diffusion models. We are optimizing models for the right target because we know what customers want, and co-designing the architecture with our inference know-how.
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.
23
22
3
319
173,538
Volkan Aydıngül retweeted
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.
192
245
249
2,902
1,969,563
Volkan Aydıngül retweeted
Back on the road! @fal is taking over Europe 🚀 August 22 - London (Tech Europe Hackathon) August 29 - Barcelona (another Tech Europe Hackathon) September 3 - Izmir (fal x HubX Meetup) September 10 - Paris (Three.js Conference) September 15 - Berlin (Agentic AI Summit) September 19 - Barcelona (HackBarna) This schedule is gonna be tough 😀 I’ll be at most of these events, but even if I’m not, someone from the fal team will be there in person. DM me if you're in any of these cities around those dates and wanna meet / catch up! Check fal[.]ai/events for more info
9
5
2
110
16,775
Volkan Aydıngül retweeted
LTX 2.5 is live on fal. Now with Diffusion Fidelity Rendering, which puts more compute into complex scenes. It’s open, customizable, and built to hack on. Train LoRAs, fine-tune on your own data and adapt it to your domain.
8
17
6
121
17,282
Volkan Aydıngül retweeted
MiniMax-H3 Realism People LoRA adds real skin texture, micro-expressions, documentary-style motion to videos. Even keeps the audio perfectly synced. huggingface.co/fal/MiniMax-H…
3
24
3
195
14,297
Volkan Aydıngül retweeted
Following this week's frontier video model launches, we're opening up early access to something we've been building. Introducing fal Agent. A creative partner for working across the best image, video, and 3D models.
19
30
26
326
104,875