cjwbw/text2video-zero

Text-to-Image Diffusion Models are Zero-Shot Video Generators

Capabilities

Negative PromptSeed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`fps`	integer	video frames per second	`4`	—
`model_name`	string	choose your model, the model should be avaliable on HF	`"dreamlike-art/dreamlike-photoreal-2.0"`	—
`motion_field_strength_x`	integer	—	`12`	min: -20, max: 20
`motion_field_strength_y`	integer	—	`12`	min: -20, max: 20
`negative_prompt`	string	Negative Prompt	`""`	—
`prompt`	string	Input Prompt	`"A horse galloping on a street"`	—
`seed`	integer	Random seed. Leave blank to randomize the seed	`—`	—
`timestep_t0`	integer	Perform DDPM steps from t0 to t1. The larger the gap between t0 and t1, the more variance between the frames. Ensure t0 < t1	`44`	—
`timestep_t1`	integer	Perform DDPM steps from t0 to t1. The larger the gap between t0 and t1, the more variance between the frames. Ensure t0 < t1	`47`	—
`video_length`	integer	Video length in seconds	`20`	—

fpsinteger

video frames per second

Default: 4

model_namestring

choose your model, the model should be avaliable on HF

Default: "dreamlike-art/dreamlike-photoreal-2.0"

motion_field_strength_xinteger

Default: 12min: -20, max: 20

motion_field_strength_yinteger

Default: 12min: -20, max: 20

negative_promptstring

Negative Prompt

Default: ""

promptstring

Input Prompt

Default: "A horse galloping on a street"

seedinteger

Random seed. Leave blank to randomize the seed

timestep_t0integer

Perform DDPM steps from t0 to t1. The larger the gap between t0 and t1, the more variance between the frames. Ensure t0 < t1

Default: 44

timestep_t1integer

Perform DDPM steps from t0 to t1. The larger the gap between t0 and t1, the more variance between the frames. Ensure t0 < t1

Default: 47

video_lengthinteger

Video length in seconds

Default: 20

Version: e671ffe4e976Updated: 7/25/202642.0K runs