Wan v2.2 A14B Text-to-Image A14B with LoRAs | Text to Image

fal-ai/wan/v2.2-a14b/text-to-image/lora

Wan 2.2's 14B model with LoRA support generates high-fidelity images with enhanced prompt alignment, style adaptability.

Inference

Commercial use

Schema

LLMs

Playground API

About

Generate an image from text prompt with LoRA support.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/wan/v2.2-a14b/text-to-image/lora", {
  input: {
    prompt: "In this breathtaking wildlife documentary, we are drawn into an intimate close-up of a majestic lion's face, framed against the backdrop of a vast African savannah at dawn. The camera captures the raw power and nobility of the creature as it gazes intently into the distance, its golden-brown fur glistening under the soft, diffused light that bathes the scene in an ethereal glow. Harsh shadows dance across its features, accentuating the deep wrinkles around its eyes and the rugged texture of its fur, each strand a testament to its age and wisdom. The static camera angle invites viewers to immerse themselves in this moment of profound stillness, where the lion's intense focus hints at an unseen presence or a distant threat. As the sun ascends, the landscape transforms into a symphony of warm hues, enhancing the serene yet tense atmosphere that envelops this extraordinary encounter with nature's untamed beauty."
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("fal-ai/wan/v2.2-a14b/text-to-image/lora", {
  input: {
    prompt: "In this breathtaking wildlife documentary, we are drawn into an intimate close-up of a majestic lion's face, framed against the backdrop of a vast African savannah at dawn. The camera captures the raw power and nobility of the creature as it gazes intently into the distance, its golden-brown fur glistening under the soft, diffused light that bathes the scene in an ethereal glow. Harsh shadows dance across its features, accentuating the deep wrinkles around its eyes and the rugged texture of its fur, each strand a testament to its age and wisdom. The static camera angle invites viewers to immerse themselves in this moment of profound stillness, where the lion's intense focus hints at an unseen presence or a distant threat. As the sun ascends, the landscape transforms into a symphony of warm hues, enhancing the serene yet tense atmosphere that envelops this extraordinary encounter with nature's untamed beauty."
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("fal-ai/wan/v2.2-a14b/text-to-image/lora", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("fal-ai/wan/v2.2-a14b/text-to-image/lora", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

prompt string* required

The text prompt to guide image generation.

negative_prompt string

Negative prompt for video generation. Default value: ""

seed integer

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 value: 27

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

guidance_scale_2 float

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 value: 4

shift float

Shift value for the image. Must be between 1.0 and 10.0. Default value: 2

loras list<LoRAWeight>

LoRA weights to be used in the inference.

reverse_video boolean

If true, the video will be reversed.

image_size ImageSize | Enum

The size of the generated image. Default value: square_hd

Possible enum values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Note: For custom image sizes, you can pass the width and height as an object:

"image_size": {
  "width": 1280,
  "height": 720
}

image_format ImageFormatEnum

The format of the output image. Default value: "jpeg"

Possible enum values: png, jpeg

{
  "prompt": "In this breathtaking wildlife documentary, we are drawn into an intimate close-up of a majestic lion's face, framed against the backdrop of a vast African savannah at dawn. The camera captures the raw power and nobility of the creature as it gazes intently into the distance, its golden-brown fur glistening under the soft, diffused light that bathes the scene in an ethereal glow. Harsh shadows dance across its features, accentuating the deep wrinkles around its eyes and the rugged texture of its fur, each strand a testament to its age and wisdom. The static camera angle invites viewers to immerse themselves in this moment of profound stillness, where the lion's intense focus hints at an unseen presence or a distant threat. As the sun ascends, the landscape transforms into a symphony of warm hues, enhancing the serene yet tense atmosphere that envelops this extraordinary encounter with nature's untamed beauty.",
  "num_inference_steps": 27,
  "enable_safety_checker": true,
  "enable_prompt_expansion": false,
  "acceleration": "regular",
  "guidance_scale": 3.5,
  "guidance_scale_2": 4,
  "shift": 2,
  "loras": [],
  "image_size": "square_hd",
  "image_format": "jpeg"
}

Output#

image File* required

The generated image file.

seed integer* required

The seed used for generation.

{
  "image": {
    "url": "https://storage.googleapis.com/falserverless/example_outputs/wan/t2i-output.png"
  }
}

Other types#

WanV2VResponse#

video File* required

The generated video file.

prompt string

The text prompt used for video generation. Default value: ""

seed integer* required

The seed used for generation.

WanSmallT2VRequest#

prompt string* required

The text prompt to guide video generation.

negative_prompt string

Negative prompt for video generation. Default value: ""

num_frames integer

Number of frames to generate. Must be between 17 to 121 (inclusive). Default value: 81

frames_per_second integer

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 number of interpolated frames is 1, the final frames per second will be 32. If adjust_fps_for_interpolation is set to false, this value will be used as-is. Default value: 24

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (580p or 720p). Default value: "720p"

Possible enum values: 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video (16:9 or 9:16). Default value: "16:9"

Possible enum values: 16:9, 9:16, 1:1

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 40

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

shift float

Shift value for the video. Must be between 1.0 and 10.0. Default value: 5

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. If None, no interpolation is applied. Default value: "film"

Possible enum values: none, film, rife

num_interpolated_frames integer

Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.

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-is. Default value: true

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

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 value: "balanced"

Possible enum values: fast, balanced, small

WanTurboI2VResponse#

video File* required

The generated video file.

prompt string

The text prompt used for video generation. Default value: ""

seed integer* required

The seed used for generation.

WanI2VRequest#

image_url string* required

URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.

prompt string* required

The text prompt to guide video generation.

num_frames integer

Number of frames to generate. Must be between 17 to 121 (inclusive). Default value: 81

frames_per_second integer

negative_prompt string

Negative prompt for video generation. Default value: ""

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (480p, 580p, or 720p). Default value: "720p"

Possible enum values: 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image. Default value: "auto"

Possible enum values: auto, 16:9, 9:16, 1:1

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 27

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

guidance_scale_2 float

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 value: 3.5

shift float

Shift value for the video. Must be between 1.0 and 10.0. Default value: 5

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. If None, no interpolation is applied. Default value: "film"

Possible enum values: none, film, rife

num_interpolated_frames integer

Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4. Default value: 1

adjust_fps_for_interpolation boolean

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

end_image_url string

URL of the end image.

WanLoRAT2VRequest#

prompt string* required

The text prompt to guide video generation.

negative_prompt string

Negative prompt for video generation. Default value: ""

num_frames integer

Number of frames to generate. Must be between 17 to 121 (inclusive). Default value: 81

frames_per_second integer

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (480p, 580p, or 720p). Default value: "720p"

Possible enum values: 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video (16:9 or 9:16). Default value: "16:9"

Possible enum values: 16:9, 9:16, 1:1

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 27

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

guidance_scale_2 float

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 value: 4

shift float

Shift value for the video. Must be between 1.0 and 10.0. Default value: 5

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. If None, no interpolation is applied. Default value: "film"

Possible enum values: none, film, rife

num_interpolated_frames integer

Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4. Default value: 1

adjust_fps_for_interpolation boolean

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

loras list<LoRAWeight>

LoRA weights to be used in the inference.

reverse_video boolean

If true, the video will be reversed.

File#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

WanDistillT2VRequest#

prompt string* required

The text prompt to guide video generation.

num_frames integer

Number of frames to generate. Must be between 17 to 121 (inclusive). Default value: 81

frames_per_second integer

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (580p or 720p). Default value: "720p"

Possible enum values: 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video (16:9 or 9:16). Default value: "16:9"

Possible enum values: 16:9, 9:16, 1:1

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 40

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 1

shift float

Shift value for the video. Must be between 1.0 and 10.0. Default value: 5

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. If None, no interpolation is applied. Default value: "film"

Possible enum values: none, film, rife

num_interpolated_frames integer

Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.

adjust_fps_for_interpolation boolean

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

WanSmallI2VResponse#

video File* required

The generated video file.

prompt string

The text prompt used for video generation. Default value: ""

seed integer* required

The seed used for generation.

WanT2VResponse#

video File* required

The generated video file.

prompt string

The text prompt used for video generation. Default value: ""

seed integer* required

The seed used for generation.

WanSmallT2IResponse#

image File* required

The generated image file.

seed integer* required

The seed used for generation.

WanSmallI2VRequest#

image_url string* required

URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.

prompt string* required

The text prompt to guide video generation.

num_frames integer

Number of frames to generate. Must be between 17 to 121 (inclusive). Default value: 81

frames_per_second integer

negative_prompt string

Negative prompt for video generation. Default value: ""

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (580p or 720p). Default value: "720p"

Possible enum values: 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image. Default value: "auto"

Possible enum values: auto, 16:9, 9:16, 1:1

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 40

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

shift float

Shift value for the video. Must be between 1.0 and 10.0. Default value: 5

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. If None, no interpolation is applied. Default value: "film"

Possible enum values: none, film, rife

num_interpolated_frames integer

Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.

adjust_fps_for_interpolation boolean

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

WanSmallT2VResponse#

video File* required

The generated video file.

prompt string

The text prompt used for video generation. Default value: ""

seed integer* required

The seed used for generation.

ImageSize#

width integer

The width of the generated image. Default value: 512

height integer

The height of the generated image. Default value: 512

WanI2IResponse#

image File* required

The generated image file.

prompt string

The text prompt used for image generation. Default value: ""

seed integer* required

The seed used for generation.

WanSmallFastVideoT2VResponse#

video File* required

The generated video file.

prompt string

The text prompt used for video generation. Default value: ""

seed integer* required

The seed used for generation.

WanT2VRequest#

prompt string* required

The text prompt to guide video generation.

negative_prompt string

Negative prompt for video generation. Default value: ""

num_frames integer

Number of frames to generate. Must be between 17 to 121 (inclusive). Default value: 81

frames_per_second integer

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (480p, 580p, or 720p). Default value: "720p"

Possible enum values: 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video (16:9 or 9:16). Default value: "16:9"

Possible enum values: 16:9, 9:16, 1:1

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 27

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

guidance_scale_2 float

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 value: 4

shift float

Shift value for the video. Must be between 1.0 and 10.0. Default value: 5

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. If None, no interpolation is applied. Default value: "film"

Possible enum values: none, film, rife

num_interpolated_frames integer

Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4. Default value: 1

adjust_fps_for_interpolation boolean

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

WanI2IRequest#

image_url string* required

URL of the input image.

prompt string* required

The text prompt to guide image generation.

strength float

Denoising strength. 1.0 = fully remake; 0.0 = preserve original. Default value: 0.5

negative_prompt string

Negative prompt for video generation. Default value: ""

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (480p, 580p, or 720p). Default value: "720p"

Possible enum values: 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated image. If 'auto', the aspect ratio will be determined automatically based on the input image. Default value: "auto"

Possible enum values: auto, 16:9, 9:16, 1:1

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 27

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

guidance_scale float

Classifier-free guidance scale. Default value: 3.5

guidance_scale_2 float

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 value: 4

shift float

Default value: 2

image_size ImageSize | Enum

Possible enum values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Note: For custom image sizes, you can pass the width and height as an object:

"image_size": {
  "width": 1280,
  "height": 720
}

image_format ImageFormatEnum

The format of the output image. Default value: "jpeg"

Possible enum values: png, jpeg

WanT2IRequest#

prompt string* required

The text prompt to guide image generation.

negative_prompt string

Negative prompt for video generation. Default value: ""

seed integer

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 value: 27

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

guidance_scale_2 float

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 value: 4

shift float

Shift value for the image. Must be between 1.0 and 10.0. Default value: 2

image_size ImageSize | Enum

The size of the generated image. Default value: square_hd

Possible enum values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Note: For custom image sizes, you can pass the width and height as an object:

"image_size": {
  "width": 1280,
  "height": 720
}

WanTurboT2VRequest#

prompt string* required

The text prompt to guide video generation.

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (480p, 580p, or 720p). Default value: "720p"

Possible enum values: 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video (16:9 or 9:16). Default value: "16:9"

Possible enum values: 16:9, 9:16, 1:1

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

WanLoRAI2VRequest#

image_url string* required

URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.

prompt string* required

The text prompt to guide video generation.

num_frames integer

Number of frames to generate. Must be between 17 to 121 (inclusive). Default value: 81

frames_per_second integer

negative_prompt string

Negative prompt for video generation. Default value: ""

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (480p, 580p, or 720p). Default value: "720p"

Possible enum values: 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image. Default value: "auto"

Possible enum values: auto, 16:9, 9:16, 1:1

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 27

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

guidance_scale_2 float

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 value: 4

shift float

Shift value for the video. Must be between 1.0 and 10.0. Default value: 5

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. If None, no interpolation is applied. Default value: "film"

Possible enum values: none, film, rife

num_interpolated_frames integer

Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4. Default value: 1

adjust_fps_for_interpolation boolean

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

loras list<LoRAWeight>

LoRA weights to be used in the inference.

reverse_video boolean

If true, the video will be reversed.

WanSmallT2IRequest#

prompt string* required

The text prompt to guide image generation.

negative_prompt string

Negative prompt for video generation. Default value: ""

seed integer

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 value: 40

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

shift float

Shift value for the image. Must be between 1.0 and 10.0. Default value: 2

image_size ImageSize | Enum

The size of the generated image. Default value: square_hd

Possible enum values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Note: For custom image sizes, you can pass the width and height as an object:

"image_size": {
  "width": 1280,
  "height": 720
}

image_format ImageFormatEnum

The format of the output image. Default value: "jpeg"

Possible enum values: png, jpeg

WanI2VResponse#

video File* required

The generated video file.

prompt string

The text prompt used for video generation. Default value: ""

seed integer* required

The seed used for generation.

LoRAWeight#

path string* required

URL or the path to the LoRA weights.

weight_name string

Name of the LoRA weight. Used only if path is a Hugging Face repository, and required only if you have more than 1 safetensors file in the repo.

scale float

The scale of the LoRA weight. This is used to scale the LoRA weight before merging it with the base model. Default value: 1

transformer TransformerEnum

Specifies the transformer to load the lora weight into. 'high' loads into the high-noise transformer, 'low' loads it into the low-noise transformer, while 'both' loads the LoRA into both transformers. Default value: "high"

Possible enum values: high, low, both

WanV2VRequest#

video_url string* required

URL of the input video.

prompt string* required

The text prompt to guide video generation.

strength float

Strength of the video transformation. A value of 1.0 means the output will be completely based on the prompt, while a value of 0.0 means the output will be identical to the input video. Default value: 0.9

num_frames integer

Number of frames to generate. Must be between 17 to 121 (inclusive). Default value: 81

frames_per_second integer

negative_prompt string

Negative prompt for video generation. Default value: ""

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (480p, 580p, or 720p). Default value: "720p"

Possible enum values: 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input video. Default value: "auto"

Possible enum values: auto, 16:9, 9:16, 1:1

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 27

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

guidance_scale_2 float

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 value: 4

shift float

Shift value for the video. Must be between 1.0 and 10.0. Default value: 5

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. If None, no interpolation is applied. Default value: "film"

Possible enum values: none, film, rife

num_interpolated_frames integer

Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4. Default value: 1

adjust_fps_for_interpolation boolean

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

resample_fps boolean

If true, the video will be resampled to the passed frames per second. If false, the video will not be resampled.

WanS2VResponse#

video File* required

The generated video file.

WanTurboI2VRequest#

image_url string* required

URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.

prompt string* required

The text prompt to guide video generation.

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (480p, 580p, or 720p). Default value: "720p"

Possible enum values: 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image. Default value: "auto"

Possible enum values: auto, 16:9, 9:16, 1:1

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

acceleration AccelerationEnum

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. Default value: "regular"

Possible enum values: none, regular

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

end_image_url string

URL of the end image.

WanSmallFastVideoT2VRequest#

prompt string* required

The text prompt to guide video generation.

negative_prompt string

Negative prompt for video generation. Default value: ""

num_frames integer

Number of frames to generate. Must be between 17 to 121 (inclusive). Default value: 81

frames_per_second integer

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (580p or 720p). Default value: "720p"

Possible enum values: 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video (16:9 or 9:16). Default value: "16:9"

Possible enum values: 16:9, 9:16, 1:1

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

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.

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. If None, no interpolation is applied. Default value: "film"

Possible enum values: none, film, rife

num_interpolated_frames integer

Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.

adjust_fps_for_interpolation boolean

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

WanTurboT2VResponse#

video File* required

The generated video file.

prompt string

The text prompt used for video generation. Default value: ""

seed integer* required

The seed used for generation.

WanS2VRequest#

prompt string* required

The text prompt used for video generation.

negative_prompt string

Negative prompt for video generation. Default value: ""

num_frames integer

Number of frames to generate. Must be between 40 to 120, (must be multiple of 4). Default value: 80

frames_per_second integer

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

resolution ResolutionEnum

Resolution of the generated video (480p, 580p, or 720p). Default value: "480p"

Possible enum values: 480p, 580p, 720p

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 27

enable_safety_checker boolean

If set to true, input data will be checked for safety before processing.

guidance_scale float

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. Default value: 3.5

shift float

Shift value for the video. Must be between 1.0 and 10.0. Default value: 5

video_quality VideoQualityEnum

The quality of the output video. Higher quality means better visual quality but larger file size. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

Possible enum values: fast, balanced, small

image_url string* required

URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.

audio_url string* required

The URL of the audio file.

Wan v2.2 A14B Text-to-Image A14B with LoRAs Text to Image

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

WanV2VResponse#

WanSmallT2VRequest#

WanTurboI2VResponse#

WanI2VRequest#

WanLoRAT2VRequest#

File#

WanDistillT2VRequest#

WanSmallI2VResponse#

WanT2VResponse#

WanSmallT2IResponse#

WanSmallI2VRequest#

WanSmallT2VResponse#

ImageSize#

WanI2IResponse#

WanSmallFastVideoT2VResponse#

WanT2VRequest#

WanI2IRequest#

WanT2IRequest#

WanTurboT2VRequest#

WanLoRAI2VRequest#

WanSmallT2IRequest#

WanI2VResponse#

LoRAWeight#

WanV2VRequest#

WanS2VResponse#

WanTurboI2VRequest#

WanSmallFastVideoT2VRequest#

WanTurboT2VResponse#

WanS2VRequest#

Related Models