Pruna AI launches P-Video-2: 20s 1080p/48fps video from text, image or audio, from $0.015/s
Scobleizer · x · 2026-09-11
Pruna AI announced P-Video-2, pitched as the fastest text/image/audio-to-video generation mode:
- Inputs: text, image, or audio-conditioned generation; model can also pick clip length from the prompt
- Output: up to 20s, up to 1080p at 24 or 48 fps
- Speed: draft from 0.41 s/s, standard from 0.91 s/s; draft mode offers faster previews at half price
- Pricing: draft from $0.015/s, standard from $0.025/s
- Controls: optional last-frame image, seed, aspect ratio, prompt upsampling
- Available via inference partners including Replicate, Cloudflare, RunPod, Segmind, eachlabs; benchmarks coming soon. A Pruna × Ideogram text-to-image playground also offers five thinking tiers trading speed/price/quality, 1K-2K output from $0.003/run, and structured JSON prompts for layout control
Related event: Pruna AI launches P-Video-2 for fast 20-second 1080p video generation(2 posts)→
More from Multimodal
- I tested 11 video upscaling methods for AI video: local, Topaz and cloud compared — lopas99 · 2026-10-28
- AI Horde adds Moss-Image for free, no-account image generation on volunteer GPUs — Wanabeelee2 · 2026-10-28
- AI band Techhalla reimagines Slipknot's 'Wait and Bleed' as a 1971 soul performance — Mother-Pear-2392 · 2026-10-28
- Inside the Hailuo H3 Max retro-MV workflow: 15-second chunks, one reference image, multi-shot prompts — techhalla · 2026-10-28
- Open-source pipeline turns Seedance AI video into real PBR textures on your 3D mesh — OdinLovis · 2026-10-28
- AI-generated cyberpunk short 'VHS Sirens' shows off consistent characters and neon city detail — brythehuman · 2026-10-28