image-to-video
LTX-2 19b is the first DiT-based audio-video foundation model with synchronized audio and video, high fidelity, multiple performance modes, and production-ready outputs in one model. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
Your request will cost $0.08 per run.
For $1 you can run this model approximately 12 times.
One more thing::
ExamplesView all
README
LTX-2 19B Image-to-Video with Audio
LTX-2 is the first DiT-based (Diffusion Transformer) audio-video foundation model, capable of generating synchronized audio and video from a reference image and text prompt. With 19 billion parameters, it animates your input image into a high-fidelity video clip with natural sound that matches the motion — no separate audio production needed.
Why Choose This?
-
Image-conditioned video with audio Transforms a static image into a moving video with synchronized audio generated in a single pass.
-
Preserves input composition Maintains the subject, framing, and lighting of your reference image while adding natural motion.
-
High-fidelity output Leverages a 19B-parameter DiT architecture for detailed, temporally consistent video with minimal flickering.
-
Flexible resolution Supports 480p, 720p, and 1080p outputs to balance quality and cost.
-
Variable duration Generate clips from 5 to 20 seconds.
Parameters
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Reference image to animate (JPG or PNG) |
| prompt | Yes | Text description of motion, action, and audio cues |
| resolution | No | Output resolution: 480p, 720p (default), or 1080p |
| duration | No | Video length in seconds (5-20) |
| seed | No | Random seed for reproducibility (-1 for random) |
Resolution Options
| Resolution | Best For |
|---|---|
| 480p | Fast previews, iteration, lowest cost |
| 720p | Balanced quality and cost (default) |
| 1080p | Final delivery, maximum detail |
How to Use
- Upload your image — the reference image that defines subject, composition, and lighting.
- Write your prompt — describe the motion, camera movement, and audio cues.
- Select resolution — 480p for iteration, 720p for balance, 1080p for final output.
- Set duration — 5-20 seconds based on your content needs.
- Run — submit and download the animated video with synchronized audio.
Pricing
| Resolution | 5s | 10s | 15s | 20s |
|---|---|---|---|---|
| 480p | $0.06 | $0.12 | $0.18 | $0.24 |
| 720p | $0.08 | $0.16 | $0.24 | $0.32 |
| 1080p | $0.12 | $0.24 | $0.36 | $0.48 |
Billing Rules
- Base price: $0.08 (720p, 5 seconds)
- Resolution multiplier: 480p = 0.75×, 720p = 1×, 1080p = 1.5×
- Duration: Scales linearly (per 5 seconds)
- Total cost = duration × $0.08 × resolution_multiplier / 5
Best Use Cases
- Product Animation — Bring product photos to life with subtle motion and ambient audio.
- Portrait Animation — Animate headshots and portraits with natural movement.
- Social Media — Create engaging animated content from static images.
- Marketing — Transform key visuals into video ads with cohesive sound.
- Storytelling — Animate storyboard frames or concept art.
Pro Tips
- Audio is automatic — sound is generated based on visual motion and prompt context.
- Describe specific audio when needed (e.g., "rain," "jazz," "crowd noise").
- Use high-quality, sharp, well-exposed images for best results.
- Keep motion prompts simple — one clear action per prompt yields better results.
- Iterate at 480p to dial in motion, then render at higher resolution for final output.
- Use fixed seed when comparing prompt variations to isolate changes.
Notes
- Maximum video duration is 20 seconds.
- The aspect ratio of output video is influenced by your input image.
- For longer content, generate multiple clips and edit together.
Related Models
- LTX-2 19B Text-to-Video — Generate video with audio from text only, no input image required.
- Wan 2.5 I2V — Alternative image-to-video with the Wan ecosystem.
- Kling 2.6 I2V — Kuaishou's latest image-to-video generation model.
- Veo 3.1 I2V — Google's image-to-video model with high fidelity.