Skip to main content
MindStudio
Pricing
BlogAbout
My Workspace
Video Generation Model

LTX-2.3 LoRA

LTX-2.3 LoRA is a video generation model from Lightricks that supports text-to-video, image-to-video, and custom LoRA fine-tuning.

PublisherLightricks
TypeVideo
Context Window1,000 tokens
ReleasedMarch 2026
Price$0.15-$1/video
ProviderWaveSpeed
TEXT TO VIDEOIMAGE TO VIDEOLoRA

Text and image to video with LoRA support

LTX-2.3 LoRA is a video generation model developed by Lightricks, released in March 2026 and available through the Wavespeed provider on MindStudio. It supports both text-to-video and image-to-video generation, and is distinguished by its native support for LoRA (Low-Rank Adaptation) weights, which allow users to apply custom fine-tuned styles or subjects to generated videos. The model accepts a context window of up to 1,000 tokens and offers configurable inputs including resolution, aspect ratio, duration, and a seed value for reproducibility.

LTX-2.3 LoRA is well suited for creators and developers who need stylistically consistent video output, particularly when working with custom-trained LoRA models to match a specific visual identity or character. Pricing ranges from $0.15 to $1.00 per video depending on generation parameters. Its flexible input options — including image conditioning and adjustable aspect ratios — make it applicable to a range of use cases from social media content to prototyping animated visuals.

What LTX-2.3 LoRA supports

Text to Video

Generates video clips from a text prompt using a context window of up to 1,000 tokens to guide the output.

Image to Video

Animates a provided image into a video clip, using the uploaded image as the visual starting frame.

LoRA Support

Accepts custom LoRA weights at inference time, enabling fine-tuned styles, subjects, or characters to be applied to generated videos.

Resolution & Aspect Ratio Control

Allows users to select output resolution and aspect ratio via dedicated input controls, giving direct influence over the video's dimensions.

Seed-Based Reproducibility

Accepts a seed value as input so that identical prompts and settings can produce consistent, repeatable video outputs.

Configurable Duration

Exposes a numeric duration input so developers can control the length of the generated video clip.

Ready to build with LTX-2.3 LoRA?

Get Started Free

Common questions about LTX-2.3 LoRA

What is the context window for LTX-2.3 LoRA?

LTX-2.3 LoRA has a context window of 1,000 tokens, which governs the length and detail of the text prompt used to guide video generation.

How much does it cost to generate a video with LTX-2.3 LoRA?

Pricing ranges from $0.15 to $1.00 per video, depending on the generation parameters such as resolution and duration.

What types of LoRA weights does this model support?

The model accepts custom LoRA weights as an input at inference time. These can be used to apply fine-tuned visual styles, specific subjects, or character appearances to the generated video.

Can I use an image as input instead of just a text prompt?

Yes. LTX-2.3 LoRA supports image-to-video generation, where an uploaded image URL is used as the conditioning frame for the output video.

Who publishes LTX-2.3 LoRA and when was it released?

LTX-2.3 LoRA is published by Lightricks and was released in March 2026. It is available on MindStudio through the Wavespeed provider.

Parameters & options

ImageImage URL
ResolutionSelect
Default: 720p
1080p720p480p
DurationNumber
Default: 5Range: 5–20
LoRAsLoRA

Up to 3 LoRAs.

Aspect RatioToggle Group
Default: 16:9
Portrait (9:16)Landscape (16:9)
SeedSeed

A specific value that is used to guide the 'randomness' of the generation.

Range: -1–2147483647

Start building with LTX-2.3 LoRA

No API keys required. Create AI-powered workflows with LTX-2.3 LoRA in minutes — free.