infery
← All models

MAGI-1 (Distilled)

magi-distilled

Video generationby Magi Distilled

MAGI-1 distilled is a faster video generation model with exceptional understanding of physical interactions and cinematic prompts

Example

Details

Accepts
text + image + video

Pricing

Price
10 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedRandom seed for reproducibility. If None, a random seed is chosen.
promptrequiredstringThe text prompt to guide video generation.
video_urlstringURL of the input video to represent the beginning of the video. If the input video does not match the chosen aspect ratio, it is resized and center cropped.
num_framesNumber of frames to generate. Must be between 96 and 192 (inclusive). Each additional 24 frames beyond 96 incurs an additional billing unit.
resolutionstringenum: 480p, 720pResolution of the generated video (480p or 720p). 480p is 0.5 billing units, and 720p is 1 billing unit.
start_frameThe frame to begin the generation from, with the remaining frames will be treated as the prefix video. The final video will contain the frames up until this number unchanged, followed by the generated frames. The default start frame is 32 frames before the end of the video, which gives optimal resul…
aspect_ratiostringenum: auto, 16:9, 9:16, 1:1Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.
num_inference_stepsintegerenum: 4, 8, 16, 32Number of inference steps for sampling. Higher values give better quality but take longer.
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked.
image_urlstringURL of the input image to represent the first frame of the video. If the input image does not match the chosen aspect ratio, it is resized and center cropped.

Output

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