LTX-2 Image to Video (I2V) in ComfyUI: Turn Images into AI Videos

About This Workflow

1. Turn a Single Image into a Video LTX-2 I2V converts one image into a smooth, realistic AI video—no manual animation needed.

2. Add Natural Motion and Expressions Animate faces, eyes, lips, and body movement for talking, singing, or reacting characters with smooth motion.

3. Use Cinematic Camera Movement Create professional camera effects like pan, zoom, dolly, and subtle handheld motion from a still image.

4. Animate Any Style or Scene Works for portraits, action shots, cozy ASMR scenes, cartoons, 3D renders, and photorealistic visuals.

5. Run Everything Locally in ComfyUI Full local control with LoRA support, high-quality upscaling, and no cloud limits—perfect for creators and filmmakers.

Required Models

Model links

Checkpoint

• ltx-2-19b-dev-fp8.safetensors

Text Encoder

• gemma_3_12B_it_fp8_e4m3fn.safetensors

Loras

• ltx-2-19b-distilled-lora-384.safetensors

• ltx-2-19b-ic-lora-detailer.safetensors

Spatial Upscale

• ltx-2-spatial-upscaler-x2-1.0.safetensors

Model Storage Location

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 checkpoints/
│   │      └── ltx-2-19b-dev-fp8.safetensors
│   ├── 📂 text_encoders/
│   │      ├── gemma_3_12B_it_fp8_e4m3fn.safetensors
│   ├── 📂 loras/ 
│   │      └── ltx-2-19b-distilled-lora-384.safetensors
│   │      └── ltx-2-19b-ic-lora-detailer.safetensors
│   ├── 📂 latent_upscale_models/ 
│          └── ltx-2-spatial-upscaler-x2-1.0.safetensors

Workflow Graph