Starlight Precise 2.5

Improved realism for AI-generated video with enhanced faces, texture detail, and text clarity

Model Overview

Starlight Precise 2.5 is a diffusion video enhancement model designed to improve realism in AI-generated video by reducing plastic or artificial artifacts. Building on Precise 2, it enhances facial detail while improving fabrics, materials, and the clarity of text, labels, and logos.

Precise 2.5 is well suited to upscale and enhance AI-generated footage that already has strong composition and structure but appears soft or slightly artificial. It also performs well on archival content where sufficient visual information exists, such as digital video footage from the 2000s onward.

Key Capabilities

  • Improved realism for AI-generated video with more natural faces, materials, and textures

  • Enhanced rendering of text, labels, and fine detail for higher fidelity results

  • Broad applicability across GenAI and modern archival footage with consistent, stable outputs

Pricing

Frames Per Credit — 1080p
Frames Per Credit — 4k

~26

~12

circle-info

For more accurate estimates we recommend checking out our Credit Calculatorarrow-up-right.

Getting Started

Endpoint

Model-Specific Parameters

  • input_frame_count — integer, optional; maximum 9000

  • creativity"low", "middle", or "high", optional

  • is_optimized_mode — boolean, default true

  • enable_clc — boolean, default true

  • video_profile — string, optional

  • video_bit_depth — integer, optional

  • video_codec — string, optional

Examples

Last updated