infery
← All models

LTX Video-0.9.7 13B Distilled

ltx-video-13b-distilled-multiconditioning

Video generationby Lightricks

Generate videos from prompts, images, and videos using LTX Video-0.9.7 13B Distilled and custom LoRA

Example

Details

Accepts
text + image + video

Pricing

Price
5 cr / video

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedRandom seed for generation
lorasarrayLoRA weights to use for generation
imagesarrayURL of images to use as conditioning
promptrequiredstringText prompt to guide generation
videosarrayVideos to use as conditioning
frame_rateintegerThe frame rate of the video.
num_framesintegerThe number of frames in the video.
resolutionstringenum: 480p, 720pResolution of the generated video.
aspect_ratiostringenum: 9:16, 1:1, 16:9, autoThe aspect ratio of the video.
expand_promptbooleanWhether to expand the prompt using a language model.
reverse_videobooleanWhether to reverse the video.
negative_promptstringNegative prompt for generation
enable_detail_passbooleanWhether 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.
constant_rate_factorintegerThe 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.
enable_safety_checkerbooleanWhether to enable the safety checker. Disabling it requires account authorization; unauthorized requests are always checked.
temporal_adain_factornumberThe 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 i…
tone_map_compression_rationumberThe 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.
first_pass_num_inference_stepsintegerNumber of inference steps during the first pass.
second_pass_skip_initial_stepsintegerThe 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.
second_pass_num_inference_stepsintegerNumber of inference steps during the second pass.

Output

FieldTypeDescription
seedintegerThe seed used for generation.
videoThe generated video file.
promptstringThe prompt used for generation.