text-to-video

Grok

2026-09-06 05:34:50

Grok Video Agent Upgraded to 1.5: Integrates Image 2.0, Enhanced Multi-Shot Continuity

Grok Imagine has upgraded its video creation agent to version 1.5, integrating the latest Image 2.0 model to improve generation quality, narrative, and multi-shot continuity. The update focuses on the agent layer, distinct from the underlying video model version 1.5 released in June. The new agent is now available on Grok web, iOS, and Android. On Arena's Text-to-Video leaderboard, grok-imagine-video-1.5-agent ranks fifth with a score of 1491, ahead of Seedance 2.5, Seedance 2.0, and MiniMax H3. The ranking is preliminary and subject to change.

1160

fal

2026-08-27 05:19:08

fal launches H3 Max with top-ranked image-to-video output and sub-3-second generation for 5-second clips

AI 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.

2440

Alibaba

2026-07-10 14:39:13

Alibaba Confirms Ownership of AI Video Model HappyHorse as It Tops Text-to-Video Rankings

Alibaba has officially confirmed that its ATH unit developed the AI video model HappyHorse. The model leads Artificial Analysis' text-to-video rankings with a 1357 Elo score and could cut post-production costs by more than 50% through efficient audiovisual synchronization.

610