nateraw / stable-diffusion-videos

Generate videos by interpolating the latent space of Stable Diffusion

  • Public
  • 58.4K runs
  • A100 (80GB)
  • GitHub
  • License
Run with an API
Playground API Examples README Versions

Run nateraw/stable-diffusion-videos with an API

Input schema

fpsinteger

Frame rate for the video.

Default
15
Minimum
5
Maximum
60
seedsstring

Random seed, separated with '|' to use different seeds for each of the prompt provided above. Leave blank to randomize the seed.

promptsstring

Input prompts, separate each prompt with '|'.

Default
"a cat | a dog | a horse"
num_stepsinteger

Steps for generating the interpolation video. Recommended to set to 3 or 5 for testing, then up it to 60-200 for better results.

Default
50
schedulerstring

Choose the scheduler

Default
"klms"
guidance_scalenumber

Scale for classifier-free guidance

Default
7.5
Minimum
1
Maximum
20
num_inference_stepsinteger

Number of denoising steps for each image generated from the prompt

Default
50
Minimum
1
Maximum
500

Output schema

Type
uri