fal.ai·Video generation

Wan-2.2 Text-to-Video A14B

/fal-ai/wan/v2.2-a14b/text-to-videoasync$0.16 / second of output

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. Returns hosted file URLs (download promptly; fal keeps them for a limited time). Billed per second of output.

Charged per second of output produced; a call that produces nothing is charged one unit.

Input

seedany
Random seed for reproducibility. If None, a random seed is chosen.
num_inference_stepsinteger
Number of inference steps for sampling. Higher values give better quality but take longer. (default 27)
shiftnumber
Shift value for the video. Must be between 1.0 and 10.0. (default 5)
video_write_modestring
The 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. (default "balanced")
fast, balanced, small
adjust_fps_for_interpolationboolean
If 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- (default true)
enable_output_safety_checkerboolean
If set to true, output video will be checked for safety after generation. (default false)
interpolator_modelstring
The model to use for frame interpolation. If None, no interpolation is applied. (default "film")
none, film, rife
promptstringrequired
The text prompt to guide video generation.
frames_per_secondany
Frames 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 (default 16)
resolutionstring
Resolution of the generated video (480p, 580p, or 720p). (default "720p")
480p, 580p, 720p
enable_prompt_expansionboolean
Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning. (default false)
aspect_ratiostring
Aspect ratio of the generated video (16:9 or 9:16). (default "16:9")
16:9, 9:16, 1:1
enable_safety_checkerboolean
If set to true, input data will be checked for safety before processing. Disabling it requires account authorization; unauthorized requests are always checked. (default false)
num_interpolated_framesinteger
Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4. (default 1)
accelerationstring
Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. (default "regular")
none, regular
negative_promptstring
Negative prompt for video generation. (default "")
num_framesinteger
Number of frames to generate. Must be between 17 to 161 (inclusive). (default 81)
video_qualitystring
The quality of the output video. Higher quality means better visual quality but larger file size. (default "high")
low, medium, high, maximum
guidance_scale_2number
Guidance 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. (default 4)
guidance_scalenumber
Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. (default 3.5)

Field	Type	Required	Description
seed	any	—	Random seed for reproducibility. If None, a random seed is chosen.
num_inference_steps	integer	—	Number of inference steps for sampling. Higher values give better quality but take longer. (default 27)
shift	number	—	Shift value for the video. Must be between 1.0 and 10.0. (default 5)
video_write_mode	string (fast, balanced, small)	—	The 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. (default "balanced")
adjust_fps_for_interpolation	boolean	—	If 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- (default true)
enable_output_safety_checker	boolean	—	If set to true, output video will be checked for safety after generation. (default false)
interpolator_model	string (none, film, rife)	—	The model to use for frame interpolation. If None, no interpolation is applied. (default "film")
prompt	string	yes	The text prompt to guide video generation.
frames_per_second	any	—	Frames 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 (default 16)
resolution	string (480p, 580p, 720p)	—	Resolution of the generated video (480p, 580p, or 720p). (default "720p")
enable_prompt_expansion	boolean	—	Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning. (default false)
aspect_ratio	string (16:9, 9:16, 1:1)	—	Aspect ratio of the generated video (16:9 or 9:16). (default "16:9")
enable_safety_checker	boolean	—	If set to true, input data will be checked for safety before processing. Disabling it requires account authorization; unauthorized requests are always checked. (default false)
num_interpolated_frames	integer	—	Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4. (default 1)
acceleration	string (none, regular)	—	Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. (default "regular")
negative_prompt	string	—	Negative prompt for video generation. (default "")
num_frames	integer	—	Number of frames to generate. Must be between 17 to 161 (inclusive). (default 81)
video_quality	string (low, medium, high, maximum)	—	The quality of the output video. Higher quality means better visual quality but larger file size. (default "high")
guidance_scale_2	number	—	Guidance 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. (default 4)
guidance_scale	number	—	Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. (default 3.5)

Run it

curl -s https://sooma.dev/v1/run \ -H "Authorization: Bearer $SOOMA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"provider":"fal","endpoint":"/fal-ai/wan/v2.2-a14b/text-to-video","input":{"prompt":"A cinematic photo of a lighthouse at dawn, soft light"}}'

Or ask your agent: it will call inspect for this schema and run it over MCP.