Models
Sora series
By Jianchao Ci, CEO & CTO4 min read2026-04-06
TL;DR
See how Sora 2 handles text-to-video and image-to-video inside KrafLayer.
Two input modes, one model
Sora 2 is available as text-to-video for prompt-only generation, and as image-to-video when you want to start from a specific frame.
Cost per generated second is the same across both variants. Duration range and resolution support are shown in the table below.
When to choose Sora 2
- Use text-to-video when you want to generate a clip from prompt only.
- Use image-to-video when you already have a starting frame and want controlled motion from that image.
- Compare Sora 2 against Kling and Seedance 2.0 when deciding between quality, speed, and cost per second.
Related KrafLayer docs
- [Video generation models](/docs/video-generation)
- [AI video generation guide](/blog/ai-video-generator-guide)
- [AI image-to-video guide](/docs/ai-image-to-video-guide)
Related KrafLayer tools
- AI Background Remover — Cut out image backgrounds.
- AI Object Eraser — Remove selected image areas.
- AI Image Upscaler — Improve image resolution.
- AI Image Restoration — Renew noisy or degraded images.
- AI Background Replacer — Generate a new background from a prompt.
- AI Mask Edit — Edit a selected image region.
- AI Reference Image Editor — Edit with cropped image references.
- AI Scene Compose — Place products into a base scene.
- AI Product Video Generator — create product videos from prompts or product images.