You're looking at a specific version of this model. Jump to the model overview.

wan-video /wan-2.2-t2v-fast:c483b1f7

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
prompt
string
Prompt for video generation
optimize_prompt
boolean
False
Translate prompt to Chinese before generation
num_frames
integer
81

Min: 81

Max: 121

Number of video frames. 81 frames give the best results
aspect_ratio
None
16:9
Aspect ratio of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px
resolution
None
480p
Resolution of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px
frames_per_second
integer
16

Min: 5

Max: 30

Frames per second. Note that the pricing of this model is based on the video duration at 16 fps
interpolate_output
boolean
True
Interpolate the generated video to 30 FPS using ffmpeg
go_fast
boolean
True
Go fast
sample_shift
number
12

Min: 1

Max: 20

Sample shift factor
seed
integer
Random seed. Leave blank for random
disable_safety_checker
boolean
False
Disable safety checker for generated video.
lora_weights_transformer
string
Load LoRA weights for transformer. Supports arbitrary .safetensors URLs from the Internet (for example, 'https://huggingface.co/Viktor1717/scandinavian-interior-style1/resolve/main/my_first_flux_lora_v1.safetensors')
lora_scale_transformer
number
1
Determines how strongly the transformer LoRA should be applied.
lora_weights_transformer_2
string
Load LoRA weights for transformer_2. Supports arbitrary .safetensors URLs from the Internet. Can be different from transformer LoRA.
lora_scale_transformer_2
number
1
Determines how strongly the transformer_2 LoRA should be applied.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}