Models
Video generation
By Jianchao Ci, CEO & CTO6 min read2026-04-06
TL;DR
Compare AI video models by input type, duration, features, and cost per second.
Text-to-video vs. image-to-video
Text-to-video models generate motion from a prompt alone. Image-to-video models animate from a starting frame, giving you direct control over the first shot.
Use the table to compare duration range, supported inputs, available controls, and cost per generated second.
How to read the table
- Input tells you whether the model starts from prompt only or from prompt plus a start frame.
- Output summarizes duration, resolution, and framing controls.
- Features call out start-frame input, end-frame guidance, audio, and other workflow-changing options.
- Price is shown in credits per generated second.
Related KrafLayer docs
- [Generation cost](/docs/generation-cost)
- [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.