Pika H3 Flex generates 15s of 4K video in as little as 7 seconds

minchoi · x · 2026-10-30

Pika's new H3 Flex model focuses on speed: 15 seconds of AI video generated in as little as 7 seconds, with 5 separate audio stems, 12 references, and 4K finishing. The poster tested it and was impressed. Open weights are coming soon.

Related event: Pika Labs open-sources H3 Flex, its first open-weight video model, topping DesignArena t2v open-weight leaderboard(21 posts)→

Original post →

More from Multimodal

• GOLD SIGNAL: Striking AI Portrait Blends Golden Ornament With Cybernetic Face — PierceLilholt · 2026-10-30
• MiniMax Reference Video tested with image reference and DLSS 5, results look convincing — Grinderius · 2026-10-30
• Canva unveils Brush, its first vision-language model for design editing — alex_verem · 2026-10-30
• Kinoloom: open-source ComfyUI film studio renders seamless LTX 2.5 takes on 8GB card — Dry-Acanthisitta-652 · 2026-10-30
• Know, then Draw: UCSD & Adobe Cut Image-Gen Training Compute 48x While Boosting DPG-Bench 10% — Yucheng Mao · 2026-10-30
• Pika H3 Flex: official 6-step vs fused 4-step Turbo LoRA compared — Illustrious_Row_9971 · 2026-10-30

Multimodal channel →