Skip to content
LAKEER.ai

Foundation Model

LTX-2.5: Real-Time Video Model

Lightricks real-time video foundation model providing a free, high-speed Higgsfield alternative.

Get the resource
Video AI

LTX-2.5 is Lightricks' flagship open foundation model capable of synthesizing high-resolution video frames at near real-time speeds.

Delivers high temporal fidelity, natural physics, and photorealistic rendering for commercial video production.

What's inside

  • 01Sub-second frame generation
  • 02Spatial-temporal transformer
  • 03Commercial license availability

Keep exploring.

All resources
ModelsOpen Source

MoCha: Video Character Replacement

End-to-end video character replacement framework with realistic motion preservation.

AI ModelView
ModelsOpen Weights

Qwen3.8-27B — OBLITERATED

Uncensored and optimized 27B parameter open-weights reasoning model.

Hugging FaceView
ModelsQuantized

Underdog Saluki 27B (Under 8 GB)

Qwen3.8-27B parameter model optimized to run locally in under 8 GB of VRAM.

Hugging FaceView