fal2026-10-20 02:35:23fal and Black Forest Labs launch FLUX 3 Max, but its speed and quality claims come with caveatsfal and Black Forest Labs have introduced FLUX 3 Max, a video generation model that fal says can produce a 10-second clip in about 12 seconds. The launch comes with a temporary discount through Nov. 7, pricing 720p output at $0.0425 per second and 1080p at $0.0725 per second. The model is available through fal’s API and web playground, with commercial use allowed, though model weights are not open. The launch pitch centers on two headline claims: image-to-video quality on par with ByteDance’s Seedance 2.5, and generation speeds up to 22 times faster. But the source material shows both points need context. The quality comparison applies only to the image-to-video leaderboard tracked by Artificial Analysis, where FLUX 3 Max and Seedance 2.5 share the same Elo score and overlapping confidence ranges. On the text-to-video leaderboard, FLUX 3 Max is listed fourth. The speed claim also rests on fal’s own testing. One chart published at launch showed Seedance 2.5 taking 277.80 seconds under the stated conditions, versus 12.45 seconds for FLUX 3 Max. A second chart posted less than three hours later used the same footnote conditions but showed Seedance 2.5 at 69.09 seconds, cutting the gap to roughly 5.5 times.440
AI livestream2026-09-08 04:36:47Streamer N3on's AI-Powered 24/7 Livestream Backfires, He Calls It a 'Experiment' After Backlash22-year-old Kick streamer N3on claimed to be the world's first AI streamer, using GPT-6 Astra and Higgsfield.ai for a non-stop livestream. But viewers saw low-quality AI slop, and the stream lasted only five hours before N3on backtracked, calling it a one-time experiment and denying it was AI.1380
fal2026-09-03 03:04:25fal rolls out H3 Max Turbo one week after launch, cutting latency and priceAI inference platform fal has introduced H3 Max Turbo, a faster and cheaper version of H3 Max just one week after the original model’s release. The new version remains based on MiniMax H3 post-training and is optimized for fal’s own inference stack. In the company’s official test for a 5-second, 768p video, generation latency fell from 3.49 seconds on H3 Max to 1.40 seconds on H3 Max Turbo, a roughly 2.5x speed gain. The tradeoff is a slight dip in quality. In fal’s internal benchmark, the original H3 Max was set at 100% quality, while Turbo scored 97%. fal said prompt understanding, aesthetics, and overall output quality were largely preserved, and added that Turbo still ranked above the original MiniMax H3 and other video models included in the same test. Pricing also moved lower. The standard 768p rate for H3 Max Turbo is $0.04 per second, half of H3 Max’s regular $0.08 per second. fal is also offering a launch promotion with a 75% discount, bringing the cost down to $0.01 per second. At that rate, generating a one-minute video costs $0.6.1660
MiniMax2026-08-31 07:28:17MiniMax H3 Max Live Reaches Twitch as AI Video Streams Keep Generating in Real Timefal engineer Rehan Sheikh has connected H3 Max directly to Twitch in an experiment that turns AI video generation into a live, continuously updating stream. Because the model can generate footage faster than viewers consume it, the system can play one segment while rendering the next in the background, making a theoretically endless broadcast possible. Sheikh described the setup as an "infinite interdimensional television," and MiniMax later reposted the experiment. fal then continued with a broader H3 Max Live test. The stream is not pre-rendered: viewers can type !prompt in the Twitch chat, and fal said new instructions can appear on screen within seconds, letting the audience shape each scene as the broadcast unfolds. According to the source material, the lack of a fixed script or running time means the program can continue as long as generation continues. The report said the key shift is speed. H3 Max has reduced waiting time to below playback time, clearing a threshold that previously kept AI video from functioning as a true live format. fal Research said H3 Max was trained on top of MiniMax’s open-source H3 and accelerated for fal’s inference system. Official figures cited in the report said it can generate a 5-second video in under 3 seconds, with throughput about 35 times that of MiniMax’s official H3 API. On Artificial Analysis’ audio-enabled ranking, its image-to-video model sits first at 1202 Elo, while its text-to-video model ranks third at 1235 Elo behind only Wan 3.0 and Gemini Omni Flash.1560
fal2026-08-27 05:19:08fal launches H3 Max with top-ranked image-to-video output and sub-3-second generation for 5-second clipsAI inference platform fal has introduced H3 Max, a video model fine-tuned from the open-source MiniMax H3. The company said the new model improves prompt understanding and visual quality while being optimized for fal’s own inference stack. On Artificial Analysis’ leaderboard for videos with audio, H3 Max ranked No. 1 in image-to-video at 1205 Elo, ahead of ByteDance’s Seedance 2.0 and the original H3. In text-to-video, it posted 1235 Elo, placing third and sitting 4 points behind Wan 3.0 in first place. fal also highlighted speed and pricing. It said a 5-second 768p video can be generated in under 3 seconds, with throughput about 35 times that of the original H3 API. At launch, H3 Max is offered at a 50% discount, with 768p pricing set at $0.04 per second, or $2.4 for one minute of video. The price will return to $0.08 per second after Sept. 1. The model currently supports up to 768p, while the original H3 can generate 2K video. fal said the initial release includes text-to-video and image-to-video, while Reference-to-Video is not yet available.2430
