LTX Video-0.9.7 I2V 480p

Generate videos from prompts and images using LTX Video-0.9.7

Features

ltx-video-v097/i2v-480p is the first DiT-based video generation model capable of generating high-quality videos in real-time.Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content.

Key Features

• High-Quality Output: Leveraging advanced 3D VAE technology, the model ensuring high-resolution video quality without compromising performance or temporal consistency.
• Hardware Optimization and Compatibility: The model is optimized for widely used GPUs and runs efficiently across a range of hardware platforms, with particular optimization for NVIDIA RTX series GPUs.
• Open Source: LTX-Video allows developers and researchers to freely access and modify the code to suit various application needs, with the flexibility to extend it for generating longer video content.

ComfyUI

ltx-video-v097/i2v-480p Reference to Video is available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.

Use Cases

• Digital influencers & avatars
• Story-driven video characters
• Personalization in marketing

Accelerated Inference

Our accelerated inference approach leverages advanced optimization technology from WavespeedAI. This innovative fusion technique significantly reduces computational overhead and latency, enabling rapid image generation without compromising quality. The entire system is designed to efficiently handle large-scale inference tasks while ensuring that real-time applications achieve an optimal balance between speed and accuracy. For further details, please refer to the blog post.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-video-v097/i2v-480p" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "image": "https://d2g64w682n9w0w.cloudfront.net/media/images/1746603052865027664_f3ifb62Z.jpg",
    "prompt": "Close-up shot zooming in on the hands and tools, capturing wood shavings and focused lighting.",
    "negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
    "size": "832*480"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Query Parameters

Result Request Parameters

Result Response Parameters