andreasjansson/stable-diffusion-animation 🔢❓📝✓ → 🖼️

▶️ 119.4K runs 📅 Aug 2022 ⚙️ Cog 0.4.4 🔗 GitHub ⚖️ License

prompt-interpolation text-to-video

About

Animate Stable Diffusion by interpolating between two prompts

Example Output

Output

Performance Metrics

133.00s Prediction Time

324.52s Total Time

All Input Parameters

{
  "width": 512,
  "height": 512,
  "prompt_end": "tall rectangular black monolith, a white room in the future with a bed, victorian details and a tall black monolith, a detailed matte painting by Wes Anderson, behance, light and space, reimagined by industrial light and magic, matte painting, criterion collection",
  "prompt_start": "tall rectangular black monolith, monkeys in the desert looking at a large tall monolith, a detailed matte painting by Wes Anderson, behance, light and space, reimagined by industrial light and magic, matte painting, criterion collection",
  "gif_ping_pong": true,
  "output_format": "mp4",
  "guidance_scale": 7.5,
  "prompt_strength": 0.9,
  "film_interpolation": true,
  "num_inference_steps": 50,
  "num_animation_frames": "25",
  "gif_frames_per_second": 20,
  "num_interpolation_steps": 5
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
width Default: 512: Width of output image
height Default: 512: Height of output image
prompt_end (required) Type: string: Prompt to end the animation with. You can include multiple prompts by separating the prompts with | (the 'pipe' character)
prompt_start (required) Type: string: Prompt to start the animation with
gif_ping_pong Type: booleanDefault: false: Whether to reverse the animation and go back to the beginning before looping
output_format Default: gif: Output file format
guidance_scale Type: numberDefault: 7.5Range: 1 - 20: Scale for classifier-free guidance
prompt_strength Type: numberDefault: 0.8: Lower prompt strength generates more coherent gifs, higher respects prompts more but can be jumpy
film_interpolation Type: booleanDefault: true: Whether to use FILM for between-frame interpolation (film-net.github.io)
intermediate_output Type: booleanDefault: false: Whether to display intermediate outputs during generation
num_inference_steps Type: integerDefault: 50Range: 1 - 500: Number of denoising steps
num_animation_frames Type: integerDefault: 10Range: 2 - 50: Number of frames to animate
gif_frames_per_second Type: integerDefault: 20Range: 1 - 50: Frames/second in output GIF
num_interpolation_steps Type: integerDefault: 5Range: 1 - 50: Number of steps to interpolate between animation frames

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Using seed: 52273
Generating initial latents for 4 steps
Generating frame 0
Generating frame 1
Generating frame 2
Generating frame 3
Generating frame 4
Generating frame 5
Generating frame 6
Generating frame 7
Generating frame 8
Generating frame 9
Generating frame 10
Generating frame 11
Generating frame 12
Generating frame 13
Generating frame 14
Generating frame 15
Generating frame 16
Generating frame 17
Generating frame 18
Generating frame 19
Generating frame 20
Generating frame 21
Generating frame 22
Generating frame 23
Generating frame 24
Interpolating images with FILM
Saving MP4

Version Details

Version ID: ca1f5e306e5721e19c473e0d094e6603f0456fe759c10715fcd6c1b79242d4a5
Version Created: November 1, 2022

Run on Replicate →