Stabel-Video-Diffusion

Stable-video-diffusion takes an input image and other adjustment parameters to generate a dynamic video based on a static image.

Try it in the Widget Center

Click this url to try this widget and copy the Pro Config template.

Usage

<TODO: enter description here, and remove useless inputs>

Input Parameters

Name	Type	Description	Default	Required
image	string	HTTP url. Input image for stable-video-diffusion.
seed	integer	Random seed for generation process. -1 means random seed	-1
decode_chunk_size	integer	Number of frames decoded at a time! This eats most VRAM. Reduce if necessary.	5
fps	integer	Number of frames per second	7
motion_bucket_id	integer	overall motion, default to 127	127
noise_aug_strength	number	Noice augmentation strength to condition	0.02

Output Parameters

Name	Type	Description	File Type
url	string	The video that was generated has been saved as an online URL. This link is temporary, so please save it for your own use	video

Output Example

success

{ // input https://image.myshell.ai/image/chat/embed_obj/40295/20240423/8555c664f6934cdeb2ef497ba4bf5d88.jpg
   "url": "https://cdn.myshell.ai/video/chat/embed_obj/40295/20240423/556e7792f1d143d0aa1379f8c5c85348.mp4"
}

fail

{
   "results": "<the example results of this widget>"
}

Detailed Guidelines