LTX-Video 13B 0.9.8 Distilled

Generate long videos from prompts and images using LTX Video-0.9.8 13B Distilled and custom LoRA

Inference$ Commercial useFrom 3 credits per run

About LTX-Video 13B 0.9.8 Distilled

Generate long videos from prompts and images using LTX Video-0.9.8 13B Distilled and custom LoRA

videoltx-videoimage-to-video

Pricing

A run with the default settings costs 3 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

prompttextarearequired

Text prompt to guide generation

negative_prompttextareadefault: "worst quality, inconsistent motion, blurry, jittery, distorted"

Negative prompt for generation

lorasjsondefault: []

LoRA weights to use for generation

resolutionselectdefault: "720p"

Resolution of the generated video.

Options: 480p, 720p

aspect_ratioselectdefault: "auto"

The aspect ratio of the video.

Options: 9:16, 1:1, 16:9, auto

seedinteger

Random seed for generation

num_framesintegerdefault: 121

The number of frames in the video.

first_pass_num_inference_stepsintegerdefault: 8

Number of inference steps during the first pass.

second_pass_num_inference_stepsintegerdefault: 8

Number of inference steps during the second pass.

second_pass_skip_initial_stepsintegerdefault: 5

The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.

frame_rateintegerdefault: 24

The frame rate of the video.

enable_prompt_expansionbooleandefault: false

Whether to expand the prompt using a language model.

reverse_videobooleandefault: false

Whether to reverse the video.

enable_safety_checkerbooleandefault: true

Whether to enable the safety checker. Disabling it requires account authorization; unauthorized requests are always checked.

enable_detail_passbooleandefault: false

Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.

temporal_adain_factornumberdefault: 0.5

The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.

tone_map_compression_rationumberdefault: 0

The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.

constant_rate_factorintegerdefault: 29

The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.

image_urlfilerequired

Image URL for Image-to-Video task

More from LTX-Video 13B 0.9.8

LTX-Video 13B 0.9.8 Distilled

Generate long videos from prompts using LTX Video-0.9.8 13B Distilled and custom LoRA

videoltx-video

text-to-video

LTX-Video 13B 0.9.8 Distilled

Generate long videos from prompts, images, and videos using LTX Video-0.9.8 13B Distilled and custom LoRA

videoltx-video

video-to-video

LTX-Video 13B 0.9.8 Distilled

Extend videos using LTX Video-0.9.8 13B Distilled and custom LoRA

ltx-videoextend

video-to-video

Related image to video models

Kling Video v3 Image to Video [Pro]

Kling 3.0 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.

image-to-video

H3 Max Image to Video

fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality

stylizedtransform

image-to-video

H3 Max Turbo Image to Video

fal's H3 Max Turbo is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality

stylizedtransform

image-to-video

Kling Video

Kling 2.5 Turbo Pro: Top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

stylizedtransform

image-to-video

H3 Max Reference to Video

stylizedtransform

image-to-video

✦ new

Kling 4.0 Image to Video

Kling 4.0 animates a starting image into a 3 to 30-second video at 720p or 1080p, with optional ending frames and per-shot prompts.

multi-shotcinematic

image-to-video

✦ new

FLUX 3 Max Image to Video

fal’s FLUX 3 Max is a post-trained variant of FLUX 3 Video, tuned for stronger prompt adherence and better visual quality while optimized for lower latency.

fastaudio

image-to-video

Kling Video v3 Image to Video [Standard]

Kling 3.0 Standard: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.

image-to-video

Seedance 2.5 US Reference to Video

US-hosted ByteDance Seedance 2.5 generates video with native audio from up to 30 images, 10 videos, and 10 audio references. Supports reference-guided generation, video editing, and extension at 480p, 720p or 1080p.

stylizedtransform

image-to-video

Wan 3.0

Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

stylizedtransform

image-to-video

Kling Video v2.6 Image to Video

Kling 2.6 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation.

image-to-video

Kling AI Avatar v2 Standard

Kling AI Avatar v2 Standard: Endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters

image-to-video