Pika-Labs/Pika-H3-Flex
image-to-video · ♥ 515 · ↓ 1.1K
- Taskimage-to-video
- Downloads1083
- Likes509
- Licenseother
image-to-video · ♥ 515 · ↓ 1.1K
Pika H3 Flex is a post-trained H3 model, designed to give professional creators the flexibility and speed to explore with precision. Optimized for greater control, it generates video with synchronized audio in six sampling steps and supports up to 12 reference inputs, with shot direction through references and prompts.
Pika’s hosted API extends this workflow with 1080p, 2K and 4K video generation, audio stems and prompt enhancement. Local open-weight inference supports native 480p / 768p video with mixed stereo audio.
Excerpt from the model card on Hugging Face ↗.
Pika-Labs/Pika-H3-Flex was first seen on Hugging Face · Trending models on Oct 30, 2026. Since then it has appeared in 224 checks on 10 different days. Its best position was #3 of 30, reached on Nov 5, 17:42 UTC. It is #22 right now, slipping from #21 to #22 over the last 6 checks.
Position on Hugging Face · Trending models at every check (lower is better).
Best rank per day (UTC).
🔥 as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 14:42 UTC it is #22, slipping from #21 to #22 over the last 6 checks.
#3 on Hugging Face · Trending models, on Nov 5, 17:42 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Oct 30, 2026 and has been on the list on 10 days (224 checks) since.
It is tagged image-to-video with pika-h3-flex on Hugging Face and has 1083 downloads under the other license.