infery
← All models

Wan-2.2 Text-to-Video A14B with LoRAs

wan-v2.2-a14b-text-to-video-lora

Video generationby Alibaba

Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts. This endpoint supports LoRAs made for Wan 2.2.

Example

Details

Accepts
text

Pricing

Price
12.5 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedRandom seed for reproducibility. If None, a random seed is chosen.
lorasarrayLoRA weights to be used in the inference.
shiftnumberShift value for the video. Must be between 1.0 and 10.0.
promptrequiredstringThe text prompt to guide video generation.
num_framesintegerNumber of frames to generate. Must be between 17 to 161 (inclusive).
resolutionstringenum: 480p, 580p, 720pResolution of the generated video (480p, 580p, or 720p).
accelerationstringenum: none, regularAcceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.
aspect_ratiostringenum: 16:9, 9:16, 1:1Aspect ratio of the generated video (16:9 or 9:16).
reverse_videobooleanIf true, the video will be reversed.
video_qualitystringenum: low, medium, high, maximumThe quality of the output video. Higher quality means better visual quality but larger file size.
guidance_scalenumberClassifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.
negative_promptstringNegative prompt for video generation.
guidance_scale_2numberGuidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model.
video_write_modestringenum: fast, balanced, smallThe write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.
frames_per_secondFrames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the …
interpolator_modelstringenum: none, film, rifeThe model to use for frame interpolation. If None, no interpolation is applied.
num_inference_stepsintegerNumber of inference steps for sampling. Higher values give better quality but take longer.
enable_safety_checkerbooleanIf set to true, input data will be checked for safety before processing. Disabling it requires account authorization; unauthorized requests are always checked.
enable_prompt_expansionbooleanWhether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.
num_interpolated_framesintegerNumber of frames to interpolate between each pair of generated frames. Must be between 0 and 4.
adjust_fps_for_interpolationbooleanIf true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-…
enable_output_safety_checkerbooleanIf set to true, output video will be checked for safety after generation.

Output

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