Back to Browse/Compare
AOpen

LTX-2

Lightricks

The predecessor to 2.3. 19B params, native 4K + audio, 30 camera moves. Still excellent and widely deployed.

AOpen

Wan 2.2

Alibaba (Tongyi Lab)

MoE architecture with 27B total params but only 14B active. Trained on 65% more images and 83% more video than 2.1. Outperforms leading closed-source models on Wan-Bench 2.0.

Pick LTX-2 if…

You want production video pipelines, camera-controlled generation, or depth/pose-driven workflows.

Pick Wan 2.2 if…

You want cinematic style control, speech-to-video, or consumer GPU deployment (TI2V-5B).

Specifications

Maker
Lightricks
Alibaba (Tongyi Lab)
Source Type
Open Source
Open Source
License
Apache 2.0 (<$10M rev)
Apache 2.0
Architecture
DiT + 3D Causal VAE
DiT + MoE (2-expert: high-noise + low-noise)
Parameters
19B (14B video + 5B audio)
27B total (14B active per step, 2x14B experts)
Max Resolution
4K
720p
Max Duration
20s
10-15s
FPS
Up to 50
24
Native Audio
Yes
No
ComfyUI Support
Yes
Yes
Fine-tunable
Yes
Yes
Min VRAM
12GB+ (distilled) / 24GB+ (full)
8GB (small) / 24GB (full)
Cost / Second
$0.04
Self-host
Inputs
T2V, I2V, V2V, Audio-to-Video, Depth, OpenPose, Camera Control
T2V (A14B), I2V (A14B), TI2V (5B), S2V (14B)
On Floyo
Yes
Yes

Strengths & Trade-offs

LTX-2

Strengths

  • +19B params (14B video + 5B audio)
  • +native 4K at 50fps
  • +first open model with unified audio-video
  • +30 cinematic camera moves
  • +depth-aware generation

Trade-offs

  • -Superseded by 2.3 on detail and audio quality
  • -LoRAs not compatible with 2.3
  • -texture drift every 8-10 frames
  • -in-scene text issues

Best For

  • →Production video pipelines
  • →camera-controlled generation
  • →depth/pose-driven workflows
  • →budget 4K content

Wan 2.2

Strengths

  • +First MoE in video diffusion
  • +27B total but only 14B active per step
  • +high-noise expert for layout + low-noise for detail
  • ++65.6% more images and +83.2% more video training data vs 2.1
  • +cinematic aesthetic control (lighting, composition, contrast, color tone)

Trade-offs

  • -720p cap
  • -MoE needs careful threshold tuning (SNR-based)
  • -no native audio in base model (S2V is separate)
  • -newer ecosystem than 2.1

Best For

  • →Self-hosted production
  • →cinematic style control
  • →speech-to-video
  • →consumer GPU deployment (TI2V-5B)

Run these models on Floyo

Browser-based ComfyUI. No setup, no GPU required.

T2VLTX-2

LTX 2 19B Fast Text to Video

3.6k runs

PreprocessingWan 2.2

Wan 2.2 Animate Preprocess (Kijai)

V2VWan 2.2

Wan 2.2 + Qwen V2V Restyle

T2VWan 2.2

Wan 2.2 T2V with UnifiedRew

CharacterWan 2.2

Wan 2.2 Animate Character Replacement

Open Floyo →