PixVerse C1 (April 2026) is the industry’s first foundation model built for film & TV production, and the most powerful model for China’s short-drama and comic-drama sector.

Key capabilities: text‑to‑video, image‑to‑video, reference‑to-video(fusion), transition.

Output: up to 15s, 1080p, with audio. All modes support prompt‑driven auto‑storyboarding, and C1's reference‑to-video(fusion) can directly turn multi‑panel storyboard images into video.

PixVerse aims to be the world’s best video generation model. C1 delivers cinematic‑grade visuals, physically plausible character motion, and hard‑hitting combat – from flesh‑to‑flesh punches to high‑intensity weapon clashes.

C1 Core Capabilities

【Cinema‑Grade DNA】– A full pipeline built for filmmaking

• Breaks single‑subject limits → precise multi‑character motion in complex scenes
• Reference image guidance keeps characters consistent across cuts and background tones unified – solving AI’s “continuity” pain point
• Up to 1080p, 15s direct output – max production efficiency

【Hardcore VFX】– Industrial‑grade evolution for action & effects

• Physics‑grounded motion: Overcomes the “no collision feel” problem. Delivers believable flesh‑to‑flesh impacts and weapon clashes.
• Aesthetic effects matrix: Optimized flow of light particles & natural elements (wind, thunder, ice, fire). Embodied modeling of traditional symbols (Tai Chi, star arrays) for distinctive fantasy visuals.
• Martial arts: Explosive moves (live‑action or anime) – sharp, well‑paced, rhythmic, both watchable and expressive.
• Fantasy/magic: Rich, believable elemental details – ethereal yet grounded, highly immersive.
• High‑speed motion: Smooth camera tracking, strong speed sense, vivid presence.

【Narrative Innovation】– Multi‑panel intelligent storyboarding

• Turn multi‑panel storyboard images into continuous video in one click. Bridges static concepts to dynamic storytelling, giving AI video a native editing feel.

C1 Rate Card